© 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. 8103
    Prev
    Next
    INDEX
    Explanations

    words related to actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    references to significant changes or movements

    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
     Pir
    -0.74
     Scand
    -0.72
     Seym
    -0.70
     Princ
    -0.66
    ashtra
    -0.66
     Spiegel
    -0.64
     Pwr
    -0.63
     Plum
    -0.63
     Buff
    -0.62
     princip
    -0.61
    POSITIVE LOGITS
    ings
    2.03
    INGS
    1.46
    ING
    1.42
    ingly
    1.41
    eless
    1.40
    estones
    1.36
    ework
    1.32
    eness
    1.32
    emen
    1.30
    eworks
    1.28
    Activations Density 0.194%

    No Known Activations