Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 18180
    Prev
    Next
    INDEX
    Explanations

    people or objects in various positions or postures

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing individuals in various positions, particularly those lying or sitting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    allo
    -0.75
    ãĥķãĤ©
    -0.73
    bits
    -0.72
    ãĤ·ãĥ£
    -0.71
    sylv
    -0.68
    ologies
    -0.67
    facts
    -0.66
    actual
    -0.66
    emin
    -0.64
     specificity
    -0.63
    POSITIVE LOGITS
     beside
    1.16
     atop
    1.15
     perched
    1.11
     slumped
    1.05
     recl
    1.02
     calmly
    1.02
     peacefully
    1.00
     seiz
    1.00
     silently
    0.99
     kneeling
    0.97
    Activations Density 0.114%

    No Known Activations