© 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. 7664
    Prev
    Next
    INDEX
    Explanations

    errors or warning messages related to invalid or incorrect input

    oai_token-act-pair · gpt-3.5-turbo

    messages indicating an invalid email address

    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
    cloth
    -0.70
    heed
    -0.69
    rooms
    -0.67
    ynthesis
    -0.65
    illance
    -0.65
    krit
    -0.63
    grad
    -0.63
    ronics
    -0.62
    zzo
    -0.62
    inker
    -0.62
    POSITIVE LOGITS
     Invalid
    0.87
    ities
    0.81
    ROR
    0.79
     Email
    0.75
    inately
    0.73
    AMI
    0.72
    ating
    0.71
    ãĥ³ãĤ¸
    0.71
    ATED
    0.70
    ity
    0.69
    Activations Density 0.017%

    No Known Activations