© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 36805
    Prev
    Next
    INDEX
    Explanations

    locations, particularly boroughs and cities

    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
    649
    +0.12
    0.7%
    519
    +0.12
    0.7%
    447
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.12
    0.07
    649
    +0.12
    0.04
    68
    +0.10
    0.05
    Negative Logits
    aneous
    -0.61
    rious
    -0.57
    eredith
    -0.51
    ischer
    -0.51
    aneously
    -0.51
    ļéĨĴ
    -0.51
    idav
    -0.51
    Äĩ
    -0.50
    ritional
    -0.50
     Maced
    -0.50
    POSITIVE LOGITS
    boro
    0.84
    borough
    0.71
    lander
    0.68
    folk
    0.67
    way
    0.67
    uits
    0.66
    hall
    0.66
    mary
    0.65
    port
    0.65
    pun
    0.63
    Activations Density 7.721%

    No Known Activations