© 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. 0-RES-JB
    11. 22358
    Prev
    Next
    INDEX
    Explanations

    keywords related to intelligence and the brand "Intel."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intelligence and espionage activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Urban
    -0.75
     trash
    -0.75
     reve
    -0.70
     Aval
    -0.69
     bro
    -0.69
     library
    -0.68
     dialog
    -0.67
     bub
    -0.67
     package
    -0.65
     tag
    -0.65
    POSITIVE LOGITS
    intelligence
    2.64
    Intel
    1.89
    merga
    1.84
    forward
    1.40
    reb
    1.26
    Mars
    1.15
     Fiorina
    1.09
    intel
    1.09
    lyak
    1.09
    parts
    1.09
    Activations Density 0.046%

    No Known Activations