© 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. 0-RES-JB
    11. 1174
    Prev
    Next
    INDEX
    Explanations

    proper nouns associated with the name "Robin"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Robin."

    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
    UM
    -0.76
    HQ
    -0.72
    ites
    -0.68
    Constructed
    -0.63
    yards
    -0.63
     CLSID
    -0.63
    ension
    -0.63
    ears
    -0.62
     boosters
    -0.62
     grades
    -0.62
    POSITIVE LOGITS
     Robin
    3.76
    Robin
    3.26
     Barney
    1.25
     ROB
    1.24
     rob
    1.21
     Damian
    1.19
     Grayson
    1.17
     Roy
    1.17
     Howard
    1.14
     Gareth
    1.09
    Activations Density 0.019%

    No Known Activations