© 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. 0-RES-JB
    6. 20469
    Prev
    Next
    INDEX
    Explanations

    references to specific groups or organizations, particularly ones involved in conflict situations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "guerrilla" and its related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Awakens
    -0.70
     Scrolls
    -0.69
    meier
    -0.69
     Magnus
    -0.68
     Kushner
    -0.67
     Township
    -0.67
    older
    -0.66
     Merge
    -0.65
     MFT
    -0.64
    ocket
    -0.64
    POSITIVE LOGITS
     gu
    3.79
    gu
    1.63
     guerrilla
    1.52
     Gu
    1.47
     GU
    1.42
    Gu
    1.41
     Guinea
    1.36
     Guan
    1.24
     Guer
    1.17
    GU
    1.15
    Activations Density 0.013%

    No Known Activations