© 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. 8830
    Prev
    Next
    INDEX
    Explanations

    words related to lobsters or medical procedures like lobotomy

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "lobster" and related terms

    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
     IST
    -0.78
    Constructed
    -0.71
     Archangel
    -0.70
    rawdownloadcloneembedreportprint
    -0.69
    Male
    -0.68
    Madison
    -0.67
     Prayer
    -0.67
    VERTIS
    -0.65
     Quadro
    -0.64
    åij
    -0.64
    POSITIVE LOGITS
    otom
    1.46
    otomy
    1.29
     Lob
    1.17
    ovy
    1.01
    omon
    0.98
    emouth
    0.97
    etooth
    0.97
    azy
    0.95
    elia
    0.95
    opa
    0.94
    Activations Density 0.006%

    No Known Activations