© 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. 11-RES-JB
    11. 21496
    Prev
    Next
    INDEX
    Explanations

    names, likely related to legal or political contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Naz," "Gab," and "Zak," indicating a focus on identifiable individuals or entities in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ESSION
    -0.73
     Gemini
    -0.65
     Progress
    -0.64
     Tens
    -0.64
    #$
    -0.60
    ãĤ¼ãĤ¦ãĤ¹
    -0.59
    lessly
    -0.59
     Cascade
    -0.59
     inst
    -0.58
     Finger
    -0.58
    POSITIVE LOGITS
    areth
    1.54
    are
    1.01
    iru
    0.97
    aret
    0.94
    arov
    0.94
    arak
    0.94
    ir
    0.93
    pha
    0.92
    ril
    0.92
    arian
    0.90
    Activations Density 0.069%

    No Known Activations