© 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. 1-RES-JB
    11. 9377
    Prev
    Next
    INDEX
    Explanations

    phrases indicating indirect suggestions or meanings

    oai_token-act-pair · gpt-3.5-turbo

    statements that suggest or indicate a certain conclusion or implication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mir
    -0.74
    HCR
    -0.72
    mar
    -0.71
    xxxx
    -0.69
     Reds
    -0.68
    ajo
    -0.66
    unker
    -0.66
    skill
    -0.66
     Chips
    -0.66
    sung
    -0.65
    POSITIVE LOGITS
     imply
    1.26
     implies
    1.15
     implied
    1.06
     infer
    0.94
     implying
    0.93
     inferred
    0.78
     extrap
    0.75
     WARRANT
    0.75
     inference
    0.75
     contradict
    0.73
    Activations Density 0.009%

    No Known Activations