© 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. 9-RES-JB
    11. 18622
    Prev
    Next
    INDEX
    Explanations

    information related to data usage and analysis

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases about data usage and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceFile
    -0.81
    quished
    -0.77
    esc
    -0.73
    cade
    -0.68
    rawdownloadcloneembedreportprint
    -0.67
    killed
    -0.66
    âĶģ
    -0.65
    Lago
    -0.65
    ILA
    -0.65
     kissed
    -0.64
    POSITIVE LOGITS
     pinpoint
    1.22
     insights
    1.20
     determine
    1.19
     determining
    1.17
     conclusions
    1.17
     insight
    1.14
     decipher
    1.12
     formulate
    1.11
     identify
    1.09
     identifying
    1.09
    Activations Density 0.617%

    No Known Activations