© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 3174
    Prev
    Next
    INDEX
    Explanations

    terms related to online communication and discussion, especially those with negative connotations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with online behavior and social interactions, particularly negative ones such as trolling and baiting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourning
    -0.48
    reetings
    -0.46
    htaking
    -0.43
    hens
    -0.43
     Occupations
    -0.43
     Anthropology
    -0.43
     Originally
    -0.43
     Highest
    -0.41
    ?",
    -0.41
     :=
    -0.40
    POSITIVE LOGITS
    ).[
    0.75
    .).
    0.74
    ]."
    0.72
    ).
    0.71
    !).
    0.65
    ?).
    0.59
    )).
    0.59
    '.
    0.57
     ).
    0.57
    }.
    0.56
    Activations Density 3.008%

    No Known Activations