© 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. 15362
    Prev
    Next
    INDEX
    Explanations

    phrases related to lack of communication or responsiveness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "respond" in various contexts

    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
    cutting
    -0.77
    than
    -0.76
     Marin
    -0.76
     Thieves
    -0.69
     Bav
    -0.69
     Demons
    -0.68
    dar
    -0.68
    fi
    -0.68
    fo
    -0.68
     Lions
    -0.68
    POSITIVE LOGITS
     favorably
    0.95
     adequately
    0.88
     Cosponsors
    0.85
    iments
    0.85
     positively
    0.84
     appropriately
    0.83
    ively
    0.81
     thereto
    0.81
     responses
    0.79
    isson
    0.79
    Activations Density 0.028%

    No Known Activations