© 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. 8-RES-JB
    11. 920
    Prev
    Next
    INDEX
    Explanations

    mentions of assistance or help requests in a community context

    oai_token-act-pair · gpt-3.5-turbo

    references to complex systems and their components

    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
    jri
    -0.67
    entimes
    -0.66
     versa
    -0.66
     theirs
    -0.65
     [*
    -0.65
     blat
    -0.64
    anwhile
    -0.64
     encour
    -0.63
     exting
    -0.62
    ļéĨĴ
    -0.62
    POSITIVE LOGITS
     Belfast
    0.79
     âĢº
    0.70
     Transgender
    0.68
     Hillary
    0.67
     Donald
    0.66
    ¶
    0.66
     Xperia
    0.65
     Hearthstone
    0.64
     graphene
    0.62
     Vegan
    0.62
    Activations Density 1.524%

    No Known Activations