© 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. 2-RES-JB
    11. 1413
    Prev
    Next
    INDEX
    Explanations

    words related to publication sources or platforms

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or topic, particularly related to the term "bl."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dangerous
    -0.68
     Expend
    -0.66
    eers
    -0.66
     Robots
    -0.66
    HER
    -0.64
     Situation
    -0.64
    OTOS
    -0.63
     Tags
    -0.63
    Gaming
    -0.63
     Gentle
    -0.61
    POSITIVE LOGITS
    anches
    1.12
    anche
    1.11
    anca
    0.99
    ossom
    0.97
    aded
    0.96
    bl
    0.96
    itzer
    0.95
    ows
    0.94
    estone
    0.94
    ight
    0.93
    Activations Density 0.007%

    No Known Activations