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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33766
    Prev
    Next
    INDEX
    Explanations

    phrases related to returning to a place or situation

    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
    +0.24
    1.0%
    240
    +0.11
    0.5%
    223
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.24
    0.07
    566
    +0.11
    0.09
    223
    +0.11
    0.08
    Negative Logits
    vern
    -0.79
    ussen
    -0.78
    hemat
    -0.78
    Cola
    -0.76
    agram
    -0.74
    acht
    -0.73
    astics
    -0.73
    boss
    -0.73
    ahi
    -0.72
    warts
    -0.71
    POSITIVE LOGITS
     home
    1.04
    ees
    0.98
     HOME
    0.91
    home
    0.86
     postage
    0.80
    owship
    0.78
     Home
    0.77
     Returning
    0.76
    porting
    0.74
    nil
    0.74
    Activations Density 7.004%

    No Known Activations