© 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. 0-RES-JB
    11. 448
    Prev
    Next
    INDEX
    Explanations

    American football player positions, primarily focusing on the defensive lineup, particularly the defensive lineman (DL) position

    oai_token-act-pair · gpt-3.5-turbo

    designations or classifications, likely related to sports positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isan
    -0.74
     bacon
    -0.72
     Ottoman
    -0.71
    ortion
    -0.70
    vent
    -0.66
    eston
    -0.65
     sage
    -0.64
     Smy
    -0.63
     agric
    -0.63
     Sar
    -0.62
    POSITIVE LOGITS
     DL
    3.95
    DL
    2.77
     OL
    1.90
     DB
    1.66
     DT
    1.60
     LU
    1.59
     LS
    1.41
     DN
    1.33
     LB
    1.31
     RB
    1.31
    Activations Density 0.026%

    No Known Activations