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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45652
    Prev
    Next
    INDEX
    Explanations

    legal and medical terms

    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
    480
    +0.53
    7.9%
    87
    +0.30
    4.5%
    447
    +0.18
    2.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.53
    0.16
    266
    +0.30
    0.61
    276
    +0.18
    0.32
    Negative Logits
    ]."
    -0.23
    .''.
    -0.22
    )."
    -0.21
    */(
    -0.20
    adobe
    -0.20
    raq
    -0.19
    mitter
    -0.18
     Cosponsors
    -0.18
    alde
    -0.18
    hani
    -0.18
    POSITIVE LOGITS
    natureconservancy
    0.16
     classy
    0.15
    raltar
    0.15
     Garry
    0.14
     brutally
    0.14
     statues
    0.14
    otom
    0.14
     kernels
    0.14
    licts
    0.14
     bleach
    0.14
    Activations Density 31.894%

    No Known Activations