© 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. 11957
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name or surname, specifically "Ram."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific name or term related to an individual or entity

    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
     Dangerous
    -0.66
     kHz
    -0.64
     Yankee
    -0.63
    urses
    -0.61
     populous
    -0.59
     Morales
    -0.59
     predic
    -0.58
     Serious
    -0.57
     Wanted
    -0.57
     indifference
    -0.56
    POSITIVE LOGITS
    irez
    1.18
    ming
    1.09
    pton
    1.06
    matical
    1.05
    mers
    0.98
    atic
    0.98
    bling
    0.92
    ram
    0.91
    med
    0.89
    bles
    0.88
    Activations Density 0.009%

    No Known Activations