© 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. 3022
    Prev
    Next
    INDEX
    Explanations

    mentions of dates and numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    words related to guest membership and access permissions

    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
     scapego
    -0.68
     appell
    -0.65
     spons
    -0.65
     Mous
    -0.64
     gorilla
    -0.62
     Argon
    -0.62
     Reilly
    -0.61
     Lever
    -0.60
     Sas
    -0.59
     Murdoch
    -0.59
    POSITIVE LOGITS
    Never
    0.89
    Uncommon
    0.79
    ãĥİ
    0.78
    ilded
    0.73
    lator
    0.71
    Login
    0.71
    registered
    0.69
    arth
    0.67
    wed
    0.67
    Subject
    0.67
    Activations Density 0.043%

    No Known Activations