© 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. 18087
    Prev
    Next
    INDEX
    Explanations

    phrases or sentence fragments related to simple or straightforward explanations

    oai_token-act-pair · gpt-3.5-turbo

    the word "simply" and its variations, indicating a summarizing or clarifying tone

    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
    afort
    -0.76
     enthus
    -0.74
    amia
    -0.72
    egal
    -0.70
    roach
    -0.67
     extensively
    -0.64
    rito
    -0.63
     heavily
    -0.62
    asta
    -0.62
    emy
    -0.61
    POSITIVE LOGITS
    IFIED
    0.79
     shrugged
    0.76
    ifiable
    0.74
     stated
    0.73
     redistributed
    0.71
     ignored
    0.69
    ãģį
    0.69
     untrue
    0.68
    cos
    0.66
     cannot
    0.65
    Activations Density 0.044%

    No Known Activations