© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9408
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental positions or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental or organizational entities involved in actions or investigations

    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
     blah
    -0.76
     metab
    -0.70
     â̦"
    -0.69
     mast
    -0.68
    âĢķ
    -0.68
     prism
    -0.66
     squared
    -0.64
     Shroud
    -0.64
    â̦"
    -0.64
     shack
    -0.64
    POSITIVE LOGITS
    ptoms
    1.26
    roximately
    1.23
    inarily
    1.18
    intendent
    1.18
    icians
    1.16
    ogether
    1.15
    onents
    1.15
    culation
    1.13
    urers
    1.13
    oters
    1.12
    Activations Density 0.213%

    No Known Activations