© 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. 20012
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "From"

    oai_token-act-pair · gpt-3.5-turbo

    references indicating the source or attribution of information

    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
     fault
    -0.66
     fool
    -0.66
     bench
    -0.64
    ashi
    -0.62
    achy
    -0.60
     restraint
    -0.60
     invalid
    -0.59
     probation
    -0.58
     immune
    -0.57
     stabil
    -0.57
    POSITIVE LOGITS
     From
    2.92
    From
    2.20
     FROM
    1.79
    from
    1.55
     Through
    1.45
     Between
    1.43
     Originally
    1.35
     Into
    1.35
     Towards
    1.35
     Of
    1.28
    Activations Density 0.012%

    No Known Activations