© 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. 24020
    Prev
    Next
    INDEX
    Explanations

    symbols and characters used in text, especially arrow symbols denoting actions or directions

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    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
    anwhile
    -0.77
     scatter
    -0.70
     rooting
    -0.70
    lda
    -0.67
     downed
    -0.66
     staggered
    -0.65
    ctors
    -0.65
     swept
    -0.64
     wind
    -0.63
     detached
    -0.62
    POSITIVE LOGITS
    £
    1.12
    į
    1.05
    ¹
    1.04
    º
    1.03
    »
    0.99
    ¿
    0.98
    ĸļ
    0.95
    âĸº
    0.93
    âĢł
    0.93
    ¯
    0.92
    Activations Density 0.566%

    No Known Activations