© 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. 4-RES-JB
    11. 14809
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating a specific area or aspect of a subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to specific areas or domains of focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActive
    -0.92
     Cosponsors
    -0.74
     sqor
    -0.72
    NAS
    -0.71
     Sachs
    -0.69
    \\\\\\\\
    -0.68
    reys
    -0.67
     Picks
    -0.67
     endorse
    -0.65
    ply
    -0.64
    POSITIVE LOGITS
     turbulence
    0.72
     separation
    0.71
     scope
    0.70
     kilometers
    0.68
     divergence
    0.68
     radius
    0.68
     periphery
    0.67
     settlement
    0.66
    lev
    0.66
     vegetation
    0.65
    Activations Density 0.153%

    No Known Activations