© 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. 11-RES-JB
    11. 18824
    Prev
    Next
    INDEX
    Explanations

    instances where actions or decisions are being taken

    oai_token-act-pair · gpt-3.5-turbo

    actions or measures taken in various contexts

    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
    utters
    -0.64
     Hitch
    -0.64
    ickers
    -0.63
    olls
    -0.63
    overed
    -0.61
    anny
    -0.59
     MPG
    -0.58
    ockey
    -0.58
    bey
    -0.57
    iddled
    -0.56
    POSITIVE LOGITS
     toward
    1.07
     towards
    1.00
     against
    0.95
     internally
    0.85
     backward
    0.84
     whatsoever
    0.80
     forward
    0.75
     mitigating
    0.75
     regarding
    0.75
     backwards
    0.74
    Activations Density 0.099%

    No Known Activations