© 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. 8845
    Prev
    Next
    INDEX
    Explanations

    mentions of specific physical objects or locations related to a specific topic or context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports and physical structures, especially in the context of goalkeeping and natural formations

    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
     Dome
    -0.80
     Shack
    -0.75
     Hale
    -0.74
     Cultural
    -0.73
     Panther
    -0.73
     Hunger
    -0.72
     Punch
    -0.71
    Charge
    -0.71
    REDACTED
    -0.70
    theless
    -0.70
    POSITIVE LOGITS
    ancies
    1.18
    ials
    1.03
    anced
    1.01
    ancers
    1.01
    elines
    0.99
    ©
    0.99
    ances
    0.99
    estones
    0.96
    anc
    0.95
    aces
    0.94
    Activations Density 0.064%

    No Known Activations