© 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. 9438
    Prev
    Next
    INDEX
    Explanations

    terms related to the human arm

    oai_token-act-pair · gpt-3.5-turbo

    references to the human arm

    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
     Sound
    -0.79
     Atmosp
    -0.66
    iculty
    -0.66
    due
    -0.66
    lish
    -0.65
     Vide
    -0.63
    sound
    -0.62
    BUR
    -0.61
     Weekly
    -0.60
    ween
    -0.59
    POSITIVE LOGITS
    ament
    1.24
    aments
    1.21
    chair
    1.17
    ageddon
    1.16
     arm
    1.11
    chairs
    0.93
    atures
    0.87
    strap
    0.87
    arms
    0.87
     wrestle
    0.86
    Activations Density 0.009%

    No Known Activations