© 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. 6367
    Prev
    Next
    INDEX
    Explanations

    mentions of docking or dock-related activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to docking interfaces and processes in technology

    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
    arial
    -0.73
     Mahjong
    -0.69
    ICES
    -0.61
     Immunity
    -0.61
    enic
    -0.60
    ony
    -0.59
     Lumpur
    -0.59
    tery
    -0.58
    asma
    -0.58
    ews
    -0.58
    POSITIVE LOGITS
    ments
    1.06
    mentation
    0.93
    able
    0.93
    ensional
    0.82
    pad
    0.81
    ezvous
    0.78
    uers
    0.78
    alty
    0.77
    ment
    0.76
    ably
    0.72
    Activations Density 0.099%

    No Known Activations