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. 5989
    Prev
    Next
    INDEX
    Explanations

    mentions of official statements or communications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of officials from various organizations or governments

    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
    âĶģ
    -0.71
     flares
    -0.70
    Interstitial
    -0.69
    bows
    -0.69
    rums
    -0.67
    ï¸
    -0.66
    actionDate
    -0.63
    ocene
    -0.63
    ||||
    -0.62
    ANC
    -0.62
    POSITIVE LOGITS
    dom
    1.00
     tasked
    0.92
     overseeing
    0.90
    doms
    0.85
     briefed
    0.82
     who
    0.81
    ially
    0.80
     stationed
    0.79
     cautioned
    0.77
     testified
    0.77
    Activations Density 0.042%

    No Known Activations