© 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. 18522
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the rationale or justification behind decisions or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to factors influencing decision-making or actions

    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
     Consider
    -0.69
    hiba
    -0.69
    Consider
    -0.68
    rather
    -0.67
    iddler
    -0.63
    ãģ®ç
    -0.61
    assian
    -0.61
    ugi
    -0.61
    pez
    -0.61
    yssey
    -0.61
    POSITIVE LOGITS
     anything
    1.49
     nor
    1.48
     anymore
    1.48
     any
    1.40
     anybody
    1.14
     necessarily
    1.11
     ANY
    1.10
     either
    1.08
     anyone
    1.07
     slightest
    1.02
    Activations Density 0.442%

    No Known Activations