© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 18454
    Prev
    Next
    INDEX
    Explanations

    references to individuals with "Jr." in their name

    oai_token-act-pair · gpt-3.5-turbo

    sentences containing names or mentions of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.76
    ãĥĦ
    -0.75
    anwhile
    -0.69
     cradle
    -0.66
     snail
    -0.62
    notations
    -0.62
    istas
    -0.62
    -+-+
    -0.61
    ãĥ«
    -0.60
    epad
    -0.60
    POSITIVE LOGITS
     Speedway
    0.70
     Targ
    0.69
    /"
    0.68
    omez
    0.65
     Released
    0.64
     Clown
    0.64
     Macedonia
    0.64
     Jr
    0.62
    bernatorial
    0.62
    atana
    0.62
    Activations Density 0.028%

    No Known Activations