© 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. 11-RES-JB
    11. 4113
    Prev
    Next
    INDEX
    Explanations

    s

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or symbol used repeatedly in the text

    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
    chnology
    -0.72
     benefits
    -0.66
     yield
    -0.65
    ktop
    -0.63
     range
    -0.61
     salv
    -0.61
     targeted
    -0.60
     avenues
    -0.60
     ranges
    -0.59
     rack
    -0.59
    POSITIVE LOGITS
    cause
    1.20
    ï¸ı
    1.15
    except
    1.11
    unless
    1.09
    why
    1.08
    said
    1.08
    then
    1.08
    especially
    1.03
    BUT
    0.99
    but
    0.98
    Activations Density 0.137%

    No Known Activations