© 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. 9-RES-JB
    11. 1008
    Prev
    Next
    INDEX
    Explanations

    the concept of being far from expectations or standards

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating lack of availability or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reef
    -0.69
    seless
    -0.68
    yne
    -0.67
    urated
    -0.64
    prem
    -0.63
    yan
    -0.63
    archives
    -0.61
    ulative
    -0.60
    apo
    -0.60
    ilt
    -0.59
    POSITIVE LOGITS
     else
    1.37
    near
    1.06
    Else
    1.04
     Else
    1.03
     near
    0.99
    abouts
    0.95
     Near
    0.93
    where
    0.80
    Near
    0.78
    else
    0.75
    Activations Density 0.033%

    No Known Activations