© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 17843
    Prev
    Next
    INDEX
    Explanations

    details of rewards or bonuses offered, sometimes involving specific numbers or actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of rewards and related numerical calculations or data

    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
    chnology
    -0.79
    cham
    -0.73
     Carmen
    -0.70
    nery
    -0.69
    erers
    -0.68
    amber
    -0.65
     Beacon
    -0.65
    ertation
    -0.64
    cart
    -0.63
    emer
    -0.63
    POSITIVE LOGITS
    +
    1.68
    +.
    1.54
    +)
    1.49
     +
    1.46
    +=
    1.42
    +,
    1.37
     +=
    1.31
    +(
    1.29
     +#
    1.20
    âĪĴ
    1.16
    Activations Density 0.103%

    No Known Activations