© 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. 8-RES-JB
    11. 9007
    Prev
    Next
    INDEX
    Explanations

    adjectives related to a high level of intensity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    specific high-frequency adjectives and noun phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĢĮ
    -0.82
     �
    -0.80
     «
    -0.68
     §§
    -0.67
     Berks
    -0.64
    ãĢĮ
    -0.61
     Dres
    -0.59
     --------
    -0.57
     ¥
    -0.57
    upon
    -0.57
    POSITIVE LOGITS
    "
    1.43
    "!
    1.38
    ",
    1.36
    "?
    1.36
    "—
    1.32
    "-
    1.27
    ";
    1.26
    ".
    1.26
    "'
    1.24
    ")
    1.24
    Activations Density 0.311%

    No Known Activations