© 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. 2-RES-JB
    11. 19389
    Prev
    Next
    INDEX
    Explanations

    words related to the direction of movement or orientation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to outward and inward movements or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azo
    -0.76
    ammy
    -0.74
    INS
    -0.69
    etsk
    -0.65
    berman
    -0.64
    acea
    -0.64
    ggies
    -0.63
    miah
    -0.62
    ARI
    -0.61
    ANS
    -0.61
    POSITIVE LOGITS
     outward
    1.03
    angular
    0.83
    ly
    0.78
     manifestations
    0.78
     inward
    0.76
     lobe
    0.71
    comings
    0.70
     appearances
    0.68
     manifestation
    0.68
    entimes
    0.67
    Activations Density 0.007%

    No Known Activations