© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 11590
    Prev
    Next
    INDEX
    Explanations

    adjectives describing qualities or states

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" and phrases indicating existence, clarity, and conditions

    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
     drafts
    -0.73
     watches
    -0.73
     Write
    -0.70
     Supports
    -0.68
     DVDs
    -0.66
     caf
    -0.65
     WRITE
    -0.65
     houses
    -0.65
     craw
    -0.65
     viz
    -0.65
    POSITIVE LOGITS
     exacerbated
    0.94
    SourceFile
    0.90
     evident
    0.89
     attributable
    0.89
     partly
    0.89
     hampered
    0.88
     contagious
    0.88
     outwe
    0.87
     unden
    0.87
     borne
    0.87
    Activations Density 0.508%

    No Known Activations