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. 45340
    Prev
    Next
    INDEX
    Explanations

    mentions of houses or related terms such as driveway and home

    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
    +0.29
    1.2%
    152
    +0.22
    0.9%
    531
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.29
    0.15
    737
    +0.22
    0.09
    102
    +0.11
    0.12
    Negative Logits
    aneously
    -0.94
    aneous
    -0.84
    ICAL
    -0.75
    iferation
    -0.74
    uyomi
    -0.74
    irection
    -0.72
    iary
    -0.72
    DragonMagazine
    -0.72
    iation
    -0.71
    psey
    -0.70
    POSITIVE LOGITS
    wife
    1.64
    wives
    1.57
    keeping
    1.32
    mates
    1.20
    keeper
    1.16
    boat
    1.15
    warming
    1.14
    boats
    1.12
    mate
    1.10
    plant
    1.10
    Activations Density 6.950%

    No Known Activations