© 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. 3991
    Prev
    Next
    INDEX
    Explanations

    phrases or commands instructing someone to take a specific action

    oai_token-act-pair · gpt-3.5-turbo

    commands or requests for user feedback or interaction

    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
    alist
    -0.83
    lied
    -0.74
    andan
    -0.70
    gio
    -0.68
     Cosponsors
    -0.68
    inals
    -0.67
    reme
    -0.65
    onse
    -0.65
    ieval
    -0.62
    DX
    -0.62
    POSITIVE LOGITS
     undone
    1.03
     aside
    0.98
    overs
    0.82
     unfinished
    0.82
     behind
    0.80
     footprints
    0.75
     intact
    0.74
     untouched
    0.72
     unanswered
    0.72
     overboard
    0.70
    Activations Density 0.040%

    No Known Activations