© 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. 8-RES-JB
    11. 7657
    Prev
    Next
    INDEX
    Explanations

    words related to attacks or negative events, particularly those involving physical harm

    oai_token-act-pair · gpt-3.5-turbo

    terms related to 'ter' and written works or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    overs
    -0.69
    OWN
    -0.65
    upid
    -0.63
    ushi
    -0.62
    ooth
    -0.62
    raction
    -0.61
    EGA
    -0.61
    icably
    -0.61
     Shiv
    -0.60
    UNE
    -0.58
    POSITIVE LOGITS
    mic
    1.00
    pher
    0.93
    ping
    0.91
    borgh
    0.89
    mes
    0.82
    ciating
    0.76
    pers
    0.76
    gins
    0.76
    thing
    0.75
    rior
    0.75
    Activations Density 0.100%

    No Known Activations