© 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. 20252
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate progress or advancement towards a goal

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progress or future expectations

    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
    PLIED
    -0.63
    soType
    -0.61
    detail
    -0.60
    amples
    -0.59
    tein
    -0.58
    aida
    -0.58
     Toggle
    -0.57
    isms
    -0.57
    ecause
    -0.55
    mop
    -0.55
    POSITIVE LOGITS
     to
    0.99
     toward
    0.91
     towards
    0.82
    to
    0.70
    graded
    0.70
    llor
    0.70
    To
    0.68
     for
    0.67
    PsyNetMessage
    0.67
     inex
    0.66
    Activations Density 0.123%

    No Known Activations