© 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. 10-RES-JB
    11. 24051
    Prev
    Next
    INDEX
    Explanations

    terms related to technology, specifically focusing on words related to software and electronics such as brands, products, and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the letter 'X' and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.74
    brance
    -0.65
    PDATE
    -0.64
    ãĤ¦ãĤ¹
    -0.63
     Cla
    -0.61
     Sergeant
    -0.61
    ADVERTISEMENT
    -0.60
     brist
    -0.59
    heit
    -0.59
    enance
    -0.59
    POSITIVE LOGITS
    reme
    0.97
    Large
    0.83
    thur
    0.78
    ©¶æ
    0.78
    xes
    0.77
    onential
    0.76
    ophon
    0.76
    xxxx
    0.73
    minus
    0.73
    ox
    0.72
    Activations Density 0.089%

    No Known Activations