© 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. 11-RES-JB
    11. 17165
    Prev
    Next
    INDEX
    Explanations

    instances of specific names followed by a specific verb

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements and claims related to specific figures or industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Narr
    -0.76
    SPONSORED
    -0.74
    mentioned
    -0.72
    sed
    -0.70
     oneself
    -0.70
    emed
    -0.68
     myself
    -0.68
    Discussion
    -0.67
    then
    -0.66
    said
    -0.65
    POSITIVE LOGITS
     owes
    1.15
     will
    1.11
     unfairly
    1.11
     shouldn
    1.08
     deserves
    1.08
     should
    1.06
     violates
    1.05
     cannot
    1.00
     lacks
    1.00
     needs
    0.98
    Activations Density 0.403%

    No Known Activations