© 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. 1365
    Prev
    Next
    INDEX
    Explanations

    the word "cast" occurring in sentences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "cast"

    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
    vironment
    -0.76
    psey
    -0.72
     Hamp
    -0.72
    ffic
    -0.66
    nown
    -0.64
    COMPLE
    -0.64
    utherford
    -0.63
    ensable
    -0.63
    pps
    -0.62
    pend
    -0.62
    POSITIVE LOGITS
    aways
    1.10
     cast
    1.06
     casts
    1.06
    Cast
    0.94
    members
    0.85
    member
    0.85
    wright
    0.83
    mates
    0.82
    caster
    0.79
    away
    0.79
    Activations Density 0.012%

    No Known Activations