© 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. 10-RES-JB
    11. 17397
    Prev
    Next
    INDEX
    Explanations

    the name "Kam" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Kam"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weap
    -0.60
     oats
    -0.60
    ãģį
    -0.60
     IF
    -0.59
     starving
    -0.59
     boils
    -0.59
    ģĸ
    -0.58
     AMA
    -0.58
     frenzy
    -0.57
     migrant
    -0.57
    POSITIVE LOGITS
    akura
    1.06
    inski
    1.03
    insky
    1.03
    arin
    1.02
    imura
    0.98
    ala
    0.96
    perty
    0.96
    aran
    0.96
    atsu
    0.95
    nesty
    0.93
    Activations Density 0.020%

    No Known Activations