© 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. 699
    Prev
    Next
    INDEX
    Explanations

    statements or reported speech in relation to an action or a piece of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reported speech or quotes

    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
    iris
    -0.72
    swick
    -0.70
    EDIT
    -0.66
     PHOTO
    -0.63
    ress
    -0.60
    estern
    -0.59
    arius
    -0.59
    å¼
    -0.59
    SourceFile
    -0.59
    ï¸
    -0.58
    POSITIVE LOGITS
     TAMADRA
    0.76
     "[
    0.74
     "âĢ¦
    0.74
     regretted
    0.72
     homosexuality
    0.67
     unfit
    0.64
     amounted
    0.64
    grading
    0.64
     UFOs
    0.62
     '[
    0.62
    Activations Density 0.360%

    No Known Activations