© 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. 11-RES-JB
    11. 22631
    Prev
    Next
    INDEX
    Explanations

    phrases related to dependency or reliance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reliance or dependence on specific factors or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     downed
    -0.71
     playable
    -0.62
     punishable
    -0.62
     showc
    -0.61
     confir
    -0.60
     repeated
    -0.60
     phased
    -0.58
     soar
    -0.58
     risen
    -0.58
     inspected
    -0.57
    POSITIVE LOGITS
    onom
    0.74
     upon
    0.73
    sylv
    0.71
    wards
    0.70
    ateral
    0.66
     on
    0.66
     Towards
    0.64
    onne
    0.64
    ocus
    0.64
    on
    0.63
    Activations Density 0.106%

    No Known Activations