© 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. 10101
    Prev
    Next
    INDEX
    Explanations

    denials or refutations of certain actions or allegations

    oai_token-act-pair · gpt-3.5-turbo

    claims of denial regarding accusations or involvement in wrongdoing

    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
    soDeliveryDate
    -0.83
     ILCS
    -0.78
    ãģ®éŃĶ
    -0.69
    thumbnails
    -0.68
    natureconservancy
    -0.65
    gall
    -0.65
     Lad
    -0.62
    perse
    -0.62
     Fortress
    -0.60
    weed
    -0.59
    POSITIVE LOGITS
     paternity
    0.98
     existence
    0.94
     allegiance
    0.93
     outright
    0.85
     validity
    0.85
     affiliation
    0.85
     involvement
    0.82
     authenticity
    0.82
     legitimacy
    0.81
     consent
    0.78
    Activations Density 0.258%

    No Known Activations