© 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. 7-RES-JB
    11. 23420
    Prev
    Next
    INDEX
    Explanations

    words related to hidden or obscured things

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to underlying themes or motivations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aires
    -0.71
    emouth
    -0.66
    dayName
    -0.64
    imates
    -0.63
    amen
    -0.60
    onite
    -0.60
    Reviewer
    -0.59
     tet
    -0.59
    uum
    -0.58
    iza
    -0.58
    POSITIVE LOGITS
     Scenes
    0.74
     lies
    0.73
    neath
    0.72
     Features
    0.69
    VIEW
    0.68
     scenes
    0.68
     Madness
    0.66
    draw
    0.63
     Gloss
    0.63
     Develop
    0.61
    Activations Density 0.206%

    No Known Activations