Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 34283
    Prev
    Next
    INDEX
    Explanations

    information related to brain functions and cognitive processes

    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
    447
    +0.21
    0.9%
    540
    +0.11
    0.5%
    92
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.21
    0.20
    255
    +0.11
    0.12
    285
    +0.11
    0.07
    Negative Logits
    ulhu
    -0.96
    ranch
    -0.89
    oil
    -0.87
    çīĪ
    -0.83
    ppa
    -0.79
    ufact
    -0.78
     cess
    -0.77
    prus
    -0.76
     condem
    -0.75
    addons
    -0.75
    POSITIVE LOGITS
     stimuli
    1.35
     behaviors
    1.21
     behaviours
    1.01
     cognition
    1.01
    âĢIJ
    1.00
     behavior
    0.99
     cognitive
    0.98
     cues
    0.98
     stimulus
    0.97
     responses
    0.94
    Activations Density 12.991%

    No Known Activations