© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 10249
    Prev
    Next
    INDEX
    Explanations

    specific abstract symbols or characters that consistently appear together

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols that may indicate encoded or corrupted data

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

    No Comments

    Negative Logits
     manif
    -1.00
    espie
    -0.83
    utenberg
    -0.81
    perty
    -0.79
     handshake
    -0.74
    omorphic
    -0.74
    ocene
    -0.74
    emetery
    -0.73
     coerc
    -0.72
    othal
    -0.72
    POSITIVE LOGITS
    Ĭ
    1.02
    ¬
    0.95
    âϦ
    0.94
    天
    0.91
    ĭ
    0.88
    à¤
    0.87
    ¹
    0.87
    âķIJâķIJ
    0.87
    ECH
    0.87
    ¶æ
    0.87
    Activations Density 0.009%

    No Known Activations