© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 2772
    Prev
    Next
    INDEX
    Explanations

    actions or decisions that someone is allowed or able to make

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing consent or permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADS
    -0.66
    ruary
    -0.66
    lda
    -0.66
    livious
    -0.64
    ulp
    -0.64
     NAACP
    -0.63
    wat
    -0.63
    OV
    -0.62
     Ori
    -0.60
     NR
    -0.59
    POSITIVE LOGITS
    lich
    0.82
    .''.
    0.77
     deems
    0.69
     deem
    0.65
    Methods
    0.65
    .[
    0.65
     Chimera
    0.65
     indulge
    0.64
    .","
    0.63
     thereof
    0.62
    Activations Density 0.246%

    No Known Activations