© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20400
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to hasty actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    words related to negative characteristics or unpleasant qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     certs
    -0.71
     viol
    -0.70
     Garc
    -0.66
     incarcerated
    -0.65
     transc
    -0.62
     fulfilled
    -0.62
     bonded
    -0.61
     vis
    -0.61
     Reeves
    -0.59
     Sr
    -0.59
    POSITIVE LOGITS
    asty
    4.58
    asted
    1.77
    asting
    1.47
    asts
    1.45
    ast
    1.26
    aughty
    1.25
    aste
    1.21
    astic
    1.14
    assy
    1.13
    AST
    1.11
    Activations Density 0.020%

    No Known Activations