© 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. 6424
    Prev
    Next
    INDEX
    Explanations

    expressions of hope

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hope or desire

    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
    pes
    -0.76
    kw
    -0.67
    IDER
    -0.66
    vation
    -0.66
    inas
    -0.66
    eas
    -0.65
    atures
    -0.65
    akable
    -0.64
    ces
    -0.63
    ItemImage
    -0.62
    POSITIVE LOGITS
     someday
    1.11
     congr
    0.77
     whoever
    0.75
     you
    0.72
     somebody
    0.70
     unborn
    0.68
     expr
    0.67
    terday
    0.66
    fully
    0.65
     readers
    0.65
    Activations Density 0.030%

    No Known Activations