© 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. 8065
    Prev
    Next
    INDEX
    Explanations

    phrases containing the name "Sam"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Sam."

    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
    enture
    -0.83
    catentry
    -0.71
    opausal
    -0.69
    geon
    -0.68
     turbine
    -0.68
    oline
    -0.68
     engagements
    -0.67
     pont
    -0.67
    orset
    -0.66
     WARN
    -0.65
    POSITIVE LOGITS
     Sam
    3.53
    Sam
    2.85
    sam
    2.15
     sam
    2.02
     SAM
    1.91
    SAM
    1.80
     Sammy
    1.61
     Samuel
    1.54
     Dean
    1.25
     Samson
    1.25
    Activations Density 0.012%

    No Known Activations