© 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. 3-RES-JB
    11. 7036
    Prev
    Next
    INDEX
    Explanations

    references to the term "Horror" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Hor" followed by numbers or relevant terms, indicating a focus on a specific entity or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.94
    ãģ¦
    -0.86
    ãģ®éŃĶ
    -0.76
    0000000000000000
    -0.76
     Bakr
    -0.71
     succeeding
    -0.69
    uncture
    -0.65
    peak
    -0.65
    $$$$
    -0.65
    eer
    -0.63
    POSITIVE LOGITS
    izont
    1.30
    izontal
    1.16
    rigan
    1.09
    izons
    1.06
    rible
    1.01
    Hor
    0.95
    itialized
    0.93
    izon
    0.91
    ribly
    0.91
    oscope
    0.91
    Activations Density 0.009%

    No Known Activations