© 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. 11-RES-JB
    11. 3863
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and partnership

    oai_token-act-pair · gpt-3.5-turbo

    expressions of enthusiasm and support in a collaborative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disputed
    -0.58
     hypothetical
    -0.55
     declined
    -0.55
    ificantly
    -0.55
     negligible
    -0.55
     plurality
    -0.53
     nonexistent
    -0.53
     refusal
    -0.52
     peaked
    -0.52
    erate
    -0.52
    POSITIVE LOGITS
    !".
    1.24
    )!
    1.21
    !!
    1.18
    !).
    1.17
    !
    1.17
     ðŁĻĤ
    1.12
    !!!
    1.11
    !"
    1.10
     :)
    1.09
    !",
    1.07
    Activations Density 0.673%

    No Known Activations