Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 18432
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or institutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to education and learning environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displayText
    -0.60
    united
    -0.59
    colour
    -0.56
    pleasant
    -0.55
     festive
    -0.55
     favourable
    -0.54
     restraining
    -0.53
     Whilst
    -0.53
     è£ıç
    -0.52
    azard
    -0.52
    POSITIVE LOGITS
     someday
    0.85
     dudes
    0.82
     goddamn
    0.77
     damn
    0.76
     crap
    0.74
     shit
    0.73
     bullshit
    0.73
     nerds
    0.72
     dude
    0.72
    ocre
    0.71
    Activations Density 0.968%

    No Known Activations