© 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. 6-RES-JB
    11. 11649
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific models or equations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to climate models and simulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azar
    -0.91
    ulhu
    -0.77
    emouth
    -0.77
    olulu
    -0.74
    odore
    -0.73
     Pradesh
    -0.72
    utenberg
    -0.71
    omen
    -0.70
    avez
    -0.69
    coming
    -0.69
    POSITIVE LOGITS
     organism
    0.86
     equations
    0.82
    model
    0.80
    models
    0.79
    LAB
    0.76
     Operator
    0.75
    oufl
    0.74
     models
    0.70
     model
    0.69
     simulations
    0.69
    Activations Density 0.021%

    No Known Activations