© 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. 22489
    Prev
    Next
    INDEX
    Explanations

    specific numbers or codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical identifiers and class designations

    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
     unaff
    -0.64
     plac
    -0.62
    anooga
    -0.61
     simulac
    -0.56
     unequiv
    -0.56
     disastrous
    -0.55
     relentless
    -0.55
    ographers
    -0.55
     Bout
    -0.55
     unwelcome
    -0.54
    POSITIVE LOGITS
    58
    1.51
    79
    1.51
    84
    1.51
    70
    1.50
    81
    1.50
    57
    1.48
    76
    1.47
    59
    1.47
    88
    1.47
    71
    1.47
    Activations Density 0.188%

    No Known Activations