© 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. 18971
    Prev
    Next
    INDEX
    Explanations

    phrases indicating that information presented is noteworthy or important

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize important information or points of note

    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
     Instr
    -0.80
     throats
    -0.71
    idal
    -0.69
     hemor
    -0.66
    iew
    -0.63
     lett
    -0.62
    body
    -0.60
    goo
    -0.59
     EntityItem
    -0.59
     nomine
    -0.59
    POSITIVE LOGITS
     NOTICE
    0.78
     briefly
    0.77
    inational
    0.76
     lest
    0.73
    âĦ¢:
    0.71
     caveats
    0.69
    ARK
    0.68
    ombat
    0.67
    ]:
    0.66
     WHY
    0.65
    Activations Density 0.088%

    No Known Activations