© 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. 15179
    Prev
    Next
    INDEX
    Explanations

    words that indicate potential consequences or effects of a situation or action

    oai_token-act-pair · gpt-3.5-turbo

    concepts and discussions related to implications of various subjects or findings

    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
    vez
    -0.67
     Columb
    -0.65
    este
    -0.64
    cin
    -0.64
    vey
    -0.64
    few
    -0.64
    ten
    -0.64
    oned
    -0.64
    zig
    -0.63
    ope
    -0.62
    POSITIVE LOGITS
     implications
    1.18
     ramifications
    1.00
     Impl
    0.90
    notations
    0.85
    notation
    0.84
     implication
    0.84
     consequences
    0.82
     repercussions
    0.82
     fallout
    0.79
     ripple
    0.79
    Activations Density 0.016%

    No Known Activations