Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22608
    Prev
    Next
    INDEX
    Explanations

    actions or events related to specific activities or tasks being performed by characters

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to gameplay and character interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tone
    -0.75
    rea
    -0.68
    sw
    -0.66
    conn
    -0.66
    eur
    -0.64
    rez
    -0.61
    Bey
    -0.60
    zo
    -0.59
    gran
    -0.59
    seekers
    -0.57
    POSITIVE LOGITS
    ometimes
    1.20
    omething
    1.04
    hift
    1.01
    paces
    0.94
    hirt
    0.92
    ilver
    0.87
    ettings
    0.83
    hooting
    0.81
    ynthesis
    0.79
    heet
    0.76
    Activations Density 0.414%

    No Known Activations