© 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. 7-RES-JB
    11. 16739
    Prev
    Next
    INDEX
    Explanations

    professionals and specific groups of people related to specific subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to professional roles and responsibilities

    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
    jri
    -0.73
    Aw
    -0.69
    ometown
    -0.68
    bush
    -0.65
     Sunrise
    -0.65
     Revival
    -0.64
     Liberty
    -0.64
     Prosper
    -0.62
    Hig
    -0.61
    votes
    -0.60
    POSITIVE LOGITS
     alike
    1.05
    hip
    0.94
    hips
    0.90
     strive
    0.89
     adhere
    0.88
     prescribe
    0.88
     wishing
    0.87
     communicate
    0.84
    paces
    0.84
    umers
    0.82
    Activations Density 0.326%

    No Known Activations