© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 33169
    Prev
    Next
    INDEX
    Explanations

    social media and technology-related terms, particularly focused on messaging apps and digital communication platforms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    354
    +0.09
    0.5%
    696
    +0.09
    0.5%
    218
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.09
    0.16
    556
    +0.09
    0.13
    675
    +0.09
    0.14
    Negative Logits
    idation
    -0.64
    代
    -0.59
    odor
    -0.54
    Reviewer
    -0.53
     pend
    -0.53
    ³³³³³³³³
    -0.53
    mere
    -0.53
    ISON
    -0.53
    cit
    -0.53
    iard
    -0.52
    POSITIVE LOGITS
     happened
    0.74
     happ
    0.65
     transpired
    0.62
     happens
    0.59
    omething
    0.58
    Favorite
    0.58
    ional
    0.57
    otropic
    0.57
    !?
    0.56
     Played
    0.55
    Activations Density 8.899%

    No Known Activations