© 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. 7-RES-JB
    11. 23456
    Prev
    Next
    INDEX
    Explanations

    statements of support or opposition for various topics or causes

    oai_token-act-pair · gpt-3.5-turbo

    expressions of support or endorsement for various issues or causes

    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
    ngth
    -0.73
     proble
    -0.72
    iae
    -0.71
     nerv
    -0.69
     teasp
    -0.68
    terness
    -0.68
    ixtape
    -0.67
    vity
    -0.67
     mismatch
    -0.66
    atonin
    -0.66
    POSITIVE LOGITS
    enance
    0.78
     uncond
    0.76
     arming
    0.76
     endorsing
    0.74
     legalizing
    0.74
     reelection
    0.73
     whichever
    0.72
    Support
    0.72
    roud
    0.71
     adoption
    0.71
    Activations Density 0.101%

    No Known Activations