© 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. 20311
    Prev
    Next
    INDEX
    Explanations

    terms related to actions, events, and situations related to real-world events, such as protests, loans, meetings, and letters

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to significant events or actions

    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
     srf
    -0.73
     alike
    -0.60
    ecause
    -0.59
     *.
    -0.56
    [_
    -0.56
    vae
    -0.53
    incinn
    -0.53
    ankind
    -0.53
    Ĭ±
    -0.53
    aturdays
    -0.53
    POSITIVE LOGITS
    ieth
    0.65
    CVE
    0.62
     belonged
    0.61
    atories
    0.60
    orative
    0.58
     Canaver
    0.55
    seys
    0.53
    's
    0.53
    NSA
    0.53
    forts
    0.51
    Activations Density 0.951%

    No Known Activations