© 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. 8-RES-JB
    11. 4591
    Prev
    Next
    INDEX
    Explanations

    information related to progress, updates, and completion

    oai_token-act-pair · gpt-3.5-turbo

    references to ongoing processes or events, especially in a production or project context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     immoral
    -0.54
     rapist
    -0.52
     forbid
    -0.52
     altru
    -0.51
     blackmail
    -0.51
     jealous
    -0.50
    ophile
    -0.50
    Jews
    -0.50
    ById
    -0.50
     monopol
    -0.50
    POSITIVE LOGITS
     unfold
    0.72
     countdown
    0.70
     COMPLE
    0.69
    Setup
    0.68
     culmin
    0.67
     unfolds
    0.66
     unfolded
    0.66
     outline
    0.65
     unfolding
    0.64
     pacing
    0.63
    Activations Density 1.490%

    No Known Activations