© 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. 23916
    Prev
    Next
    INDEX
    Explanations

    action verbs in present or past tense related to physical activities

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to frustration or dissatisfaction

    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
     reluct
    -0.52
     seiz
    -0.50
     [+
    -0.49
     Malf
    -0.48
     dilemma
    -0.46
    theless
    -0.46
    ecause
    -0.45
     thanking
    -0.45
     consist
    -0.45
     VERS
    -0.44
    POSITIVE LOGITS
    )).
    0.97
    .).
    0.82
    ]).
    0.82
    ?).
    0.81
    ).
    0.80
    %).
    0.76
     ).
    0.74
    ))))
    0.71
    )))
    0.70
    )),
    0.69
    Activations Density 3.220%

    No Known Activations