Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 9028
    Prev
    Next
    INDEX
    Explanations

    the symbol "â̦"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a negative or challenging situation

    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
     ``
    -0.93
    _-
    -0.65
    .--
    -0.54
    bern
    -0.53
    tera
    -0.52
    (_
    -0.52
     -
    -0.51
    )--
    -0.50
    Versions
    -0.49
    twitch
    -0.49
    POSITIVE LOGITS
     â̦
    3.56
     â̦"
    3.08
     [â̦]
    2.43
    â̦
    2.35
    â̦.
    2.30
    â̦)
    2.27
     ...
    2.17
    â̦â̦
    2.12
    â̦]
    2.12
    â̦"
    2.03
    Activations Density 0.011%

    No Known Activations