© 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. 1048
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases asserting impossibility or the absence of a method

    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
    ilts
    -0.81
    rongh
    -0.81
    asts
    -0.79
    eg
    -0.79
     livest
    -0.78
    igl
    -0.70
    aples
    -0.69
    origin
    -0.69
    lux
    -0.68
    itton
    -0.68
    POSITIVE LOGITS
     whatsoever
    0.92
     else
    0.77
     anybody
    0.77
     anyone
    0.72
    Reviewer
    0.72
     anymore
    0.70
    ouver
    0.66
     THEY
    0.66
    point
    0.64
     around
    0.62
    Activations Density 0.036%

    No Known Activations