© 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. 10737
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames or handles with a strong emphasis on the letter 'j'

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols commonly associated with URL links

    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
    EStream
    -0.71
    enhagen
    -0.71
     Mellon
    -0.70
     Abbey
    -0.70
    heimer
    -0.69
     CONTROL
    -0.68
    EVA
    -0.67
     Exile
    -0.65
     Shelter
    -0.65
    å§«
    -0.64
    POSITIVE LOGITS
    bm
    0.96
    fc
    0.91
    pc
    0.89
    cs
    0.88
    pm
    0.88
    cp
    0.85
    ct
    0.85
    fx
    0.84
    cm
    0.83
    unit
    0.81
    Activations Density 0.152%

    No Known Activations