© 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. 33063
    Prev
    Next
    INDEX
    Explanations

    the phrase "the only thing"

    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
    +0.15
    0.7%
    160
    +0.12
    0.5%
    297
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.15
    0.07
    5
    +0.12
    0.05
    126
    +0.11
    0.05
    Negative Logits
    inav
    -0.84
    endars
    -0.74
    onz
    -0.72
    gars
    -0.70
    ilings
    -0.69
    choes
    -0.68
    brids
    -0.68
    avage
    -0.66
    geons
    -0.66
    eday
    -0.65
    POSITIVE LOGITS
     happened
    0.97
     happens
    0.90
     happening
    0.87
     transpired
    0.83
     missing
    0.83
    iverse
    0.83
     happ
    0.80
     undone
    0.77
     else
    0.75
     Valiant
    0.74
    Activations Density 4.588%

    No Known Activations