© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 15708
    Prev
    Next
    INDEX
    Explanations

    instances where the text mentions something having a minimal or insignificant impact or presence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of significance or minimal impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    draft
    -0.72
    RAFT
    -0.72
    lation
    -0.69
    othy
    -0.68
    inav
    -0.67
    thouse
    -0.67
    pub
    -0.66
    ser
    -0.66
    swick
    -0.65
     Rear
    -0.64
    POSITIVE LOGITS
     consolation
    0.80
     fuss
    0.72
     bit
    0.70
     doubt
    0.69
     amount
    0.67
     accord
    0.67
     avail
    0.66
     Bears
    0.66
    finger
    0.65
     rhy
    0.65
    Activations Density 0.021%

    No Known Activations