© 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. 19808
    Prev
    Next
    INDEX
    Explanations

    verbs related to giving instructions or making suggestions

    oai_token-act-pair · gpt-3.5-turbo

    actions that involve formal recognition, implementation, or change related to societal or legal issues

    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
    ajo
    -0.70
    aleb
    -0.58
    outh
    -0.56
     absorption
    -0.56
     nav
    -0.55
     gotta
    -0.55
     inability
    -0.55
     Ars
    -0.55
     Phi
    -0.54
     Ser
    -0.54
    POSITIVE LOGITS
    omorphic
    0.82
    quished
    0.81
     ASAP
    0.75
     sooner
    0.74
     âĶľâĶĢâĶĢ
    0.74
     by
    0.73
     alive
    0.73
     anew
    0.73
     someday
    0.72
    ynamic
    0.70
    Activations Density 0.234%

    No Known Activations