© 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. 13509
    Prev
    Next
    INDEX
    Explanations

    information related to specific dates or events

    oai_token-act-pair · gpt-3.5-turbo

    events involving accidents or incidents

    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
    lihood
    -0.80
     Bake
    -0.65
     Emin
    -0.64
     Maxim
    -0.63
    Dim
    -0.63
    tiny
    -0.60
     maxim
    -0.60
     Babel
    -0.60
     Disciple
    -0.60
    orem
    -0.60
    POSITIVE LOGITS
    okemon
    0.77
    anwhile
    0.64
    uters
    0.62
    hester
    0.60
    anamo
    0.60
    AMI
    0.59
    joining
    0.58
    staking
    0.58
    .............
    0.57
    nered
    0.57
    Activations Density 0.165%

    No Known Activations