© 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. 16911
    Prev
    Next
    INDEX
    Explanations

    words related to electronic devices specifically starting with the letter "E"

    oai_token-act-pair · gpt-3.5-turbo

    the letter "E" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the letter 'E' when it appears at the beginning of a word or abbreviation.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @danielepoterti
    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
    ioned
    -0.81
    Interstitial
    -0.70
    aining
    -0.69
    entimes
    -0.66
    atically
    -0.63
    utra
    -0.61
    vered
    -0.61
    ozy
    -0.60
    ihu
    -0.60
    cooked
    -0.59
    POSITIVE LOGITS
     E
    3.10
    E
    1.98
     e
    1.69
     EB
    1.39
     Ãī
    1.36
     Eb
    1.36
     EF
    1.35
     Es
    1.20
     EC
    1.20
     Eg
    1.17
    Activations Density 0.032%

    No Known Activations