© 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. 18587
    Prev
    Next
    INDEX
    Explanations

    information related to news articles or journalistic writing

    oai_token-act-pair · gpt-3.5-turbo

    key aspects of narrative complexity and critical evaluations within discussions

    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
     fixme
    -0.71
    si
    -0.65
     However
    -0.63
    bowl
    -0.63
    Tonight
    -0.63
    Joined
    -0.63
     (%)
    -0.62
     ILCS
    -0.61
    alde
    -0.60
    ().
    -0.60
    POSITIVE LOGITS
    etheless
    1.06
     nonetheless
    0.99
     broader
    0.67
     overshadowed
    0.65
     caution
    0.63
     quir
    0.63
     nevertheless
    0.62
     challeng
    0.61
     doubts
    0.59
     deeper
    0.59
    Activations Density 1.191%

    No Known Activations