© 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. 9-RES-JB
    11. 1045
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details, potentially related to machinery or equipment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to national identity and status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xus
    -0.78
    .}
    -0.74
    soDeliveryDate
    -0.71
    iasco
    -0.71
    emark
    -0.70
    Anyway
    -0.69
    otin
    -0.69
    ersen
    -0.69
    opian
    -0.67
    Interstitial
    -0.67
    POSITIVE LOGITS
     Unknown
    1.05
     TBA
    1.02
     None
    0.94
     unknown
    0.92
     TBD
    0.87
     varies
    0.80
     Various
    0.79
     Ong
    0.78
     unspecified
    0.77
     HUM
    0.76
    Activations Density 0.187%

    No Known Activations