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. 45358
    Prev
    Next
    INDEX
    Explanations

    names of people or organizations related to the field of music and academia

    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
    26
    +0.14
    0.6%
    211
    +0.12
    0.5%
    376
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.21
    556
    +0.12
    0.09
    348
    +0.10
    0.12
    Negative Logits
    ãĥĥãĥī
    -0.71
    åº
    -0.67
     redes
    -0.66
    TPPStreamerBot
    -0.66
    quartered
    -0.62
    ding
    -0.60
     Worldwide
    -0.60
     Spectrum
    -0.59
    etheless
    -0.59
    ATTLE
    -0.58
    POSITIVE LOGITS
    xtap
    1.32
    arez
    1.19
    Ju
    1.10
    icer
    0.97
    iced
    0.94
    illet
    0.89
    ju
    0.89
    ipers
    0.88
    illard
    0.83
    uti
    0.82
    Activations Density 7.649%

    No Known Activations