© 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. 8-RES-JB
    6. 17153
    Prev
    Next
    INDEX
    Explanations

    titles for videos or articles that are marked as must-watch or important

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest the importance or requirement to watch videos

    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
    Ͻ
    -0.72
     hoard
    -0.65
     snowball
    -0.64
     grate
    -0.64
     ashes
    -0.61
     spoof
    -0.60
     bragging
    -0.58
    rams
    -0.58
     underestimate
    -0.58
    ĺħ
    -0.57
    POSITIVE LOGITS
    ãĥ¤
    0.72
    Interstitial
    0.71
    TO
    0.70
    natureconservancy
    0.70
    SB
    0.68
     Thumbnails
    0.67
    redo
    0.67
    NOR
    0.67
    currency
    0.65
    HTTP
    0.65
    Activations Density 0.034%

    No Known Activations