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

    Neuronpedia

    APICircuit 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. 4403
    Prev
    Next
    INDEX
    Explanations

    land-related terms or phrases

    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
    +0.17
    0.8%
    288
    +0.16
    0.7%
    152
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.17
    0.12
    288
    +0.16
    0.13
    76
    +0.14
    0.08
    Negative Logits
    vernment
    -0.94
    hift
    -0.75
    aukee
    -0.73
    éĹĺ
    -0.72
    utic
    -0.72
     Qiao
    -0.70
     sidx
    -0.69
    unction
    -0.68
    èĢħ
    -0.68
     Fior
    -0.67
    POSITIVE LOGITS
    scape
    1.24
    locked
    1.15
    mass
    1.09
    grave
    1.05
    mine
    1.05
    owner
    1.03
    marks
    1.01
    lords
    0.97
    plane
    0.97
    gra
    0.96
    Activations Density 4.167%

    No Known Activations