© 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. 1-RES-JB
    11. 16877
    Prev
    Next
    INDEX
    Explanations

    words related to a specific term or concept, specifically "ang" with values of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ang" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ockets
    -0.77
    Ö¼
    -0.76
    ãĥ¯
    -0.75
    BY
    -0.73
    ãĤ£
    -0.72
    eanor
    -0.72
    CRIPTION
    -0.72
    ãĥ¼ãĥ³
    -0.72
    ãĥ¤
    -0.68
    earcher
    -0.67
    POSITIVE LOGITS
     ang
    1.23
    sty
    0.98
    enth
    0.91
    irlf
    0.83
    rog
    0.82
    strom
    0.80
    uing
    0.77
     separat
    0.76
    emouth
    0.76
    Ang
    0.76
    Activations Density 0.005%

    No Known Activations