© 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. 6-RES-JB
    11. 11673
    Prev
    Next
    INDEX
    Explanations

    personal viewpoints and reflections

    oai_token-act-pair · gpt-3.5-turbo

    contexts involving problematic behaviors or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.76
    iken
    -0.70
    DNA
    -0.67
    Target
    -0.65
    pent
    -0.65
    Template
    -0.65
    ieval
    -0.61
    dating
    -0.59
    cli
    -0.58
    cale
    -0.58
    POSITIVE LOGITS
     importantly
    0.80
     therein
    0.75
     cru
    0.69
     culmin
    0.68
     TRUMP
    0.68
     besides
    0.64
     GOODMAN
    0.63
     thereof
    0.61
     weary
    0.61
     coerc
    0.60
    Activations Density 0.364%

    No Known Activations