© 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. 4-RES-JB
    6. 8522
    Prev
    Next
    INDEX
    Explanations

    phrases related to updates and upcoming events

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "Up"

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

    No Comments

    Negative Logits
     sol
    -0.69
     sting
    -0.68
    ________________________
    -0.68
    ¯¯¯¯¯¯¯¯
    -0.63
    ][/
    -0.63
    >]
    -0.62
     enclosed
    -0.62
     den
    -0.60
     LIA
    -0.59
    minecraft
    -0.59
    POSITIVE LOGITS
    stairs
    1.33
    dates
    1.28
    grades
    1.27
    graded
    1.26
    dating
    1.24
    grading
    1.23
    stream
    0.92
    skirts
    0.89
    gradation
    0.86
    anish
    0.86
    Activations Density 0.025%

    No Known Activations