© 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. 10-RES-JB
    11. 21388
    Prev
    Next
    INDEX
    Explanations

    personal struggles or doubts expressed in first person singular pronouns

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional struggle or resilience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orthy
    -0.82
    asus
    -0.73
    default
    -0.70
    hor
    -0.68
    onica
    -0.67
    mington
    -0.67
    pecially
    -0.65
    miah
    -0.65
    uminium
    -0.64
    hash
    -0.64
    POSITIVE LOGITS
     still
    1.99
     nevertheless
    1.76
     nonetheless
    1.59
    still
    1.57
     remains
    1.46
     persists
    1.37
     remain
    1.35
     remained
    1.31
     retains
    1.26
     persisted
    1.22
    Activations Density 0.410%

    No Known Activations