© 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. 13105
    Prev
    Next
    INDEX
    Explanations

    information related to statistical numbers and reports

    oai_token-act-pair · gpt-3.5-turbo

    statistical data and trends related to social issues

    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
    sonian
    -0.74
    hai
    -0.69
    oya
    -0.67
    EXT
    -0.62
     Canaver
    -0.60
    amo
    -0.60
    bol
    -0.60
    raft
    -0.59
    awar
    -0.59
    âĶĢâĶĢâĶĢâĶĢ
    -0.59
    POSITIVE LOGITS
     median
    1.37
     Gallup
    1.35
     polled
    1.22
     percentage
    1.21
     respondents
    1.20
     surveyed
    1.20
     Median
    1.19
     percentages
    1.18
    Percent
    1.17
    percent
    1.15
    Activations Density 1.262%

    No Known Activations