© 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. 15202
    Prev
    Next
    INDEX
    Explanations

    abbreviations used in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sections or aspects of a structured document or report

    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
    sbm
    -0.69
     subord
    -0.68
    taboola
    -0.67
     behold
    -0.66
    naires
    -0.66
    omorphic
    -0.61
    omorph
    -0.61
    ãĥĥãĥĪ
    -0.59
    hof
    -0.59
    hower
    -0.59
    POSITIVE LOGITS
    EED
    1.42
    OIL
    1.30
    ORT
    1.15
    ORTS
    1.14
    ONSORED
    1.11
    ECT
    1.10
    IR
    1.02
    HER
    0.98
    ERSON
    0.96
    iral
    0.95
    Activations Density 0.019%

    No Known Activations