© 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. 12853
    Prev
    Next
    INDEX
    Explanations

    verbs related to movement into or within a physical space

    oai_token-act-pair · gpt-3.5-turbo

    references to underground or hidden structures and actions

    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
     Rally
    -0.70
     Reserved
    -0.61
    rek
    -0.59
     Joy
    -0.58
     assert
    -0.57
     revocation
    -0.57
     attRot
    -0.57
    rish
    -0.56
    eah
    -0.56
     redundancy
    -0.55
    POSITIVE LOGITS
     into
    1.81
     INTO
    1.61
    into
    1.56
     Into
    1.48
     onto
    1.20
     through
    1.18
     deeper
    1.17
     penetrate
    1.14
    through
    1.08
    Through
    1.07
    Activations Density 0.543%

    No Known Activations