© 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. 7-RES-JB
    11. 23363
    Prev
    Next
    INDEX
    Explanations

    Twitter handles with varying names and some irrelevant text

    oai_token-act-pair · gpt-3.5-turbo

    identifiers or codes related to individuals or organizations on social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shorth
    -0.73
    wcsstore
    -0.67
     beginners
    -0.66
     immunity
    -0.64
     misunder
    -0.63
     sidx
    -0.61
    lings
    -0.61
    cases
    -0.61
    dayName
    -0.60
     fundament
    -0.59
    POSITIVE LOGITS
    qq
    0.83
     CrossRef
    0.82
    ._
    0.78
    /?
    0.76
    jri
    0.74
    jj
    0.73
    ihara
    0.71
    uez
    0.70
    )].
    0.70
    tsky
    0.69
    Activations Density 0.051%

    No Known Activations