© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19158
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a call for action or change

    oai_token-act-pair · gpt-3.5-turbo

    phrases that advocate for an end to various issues or problems

    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
    wake
    -0.79
    é¾įåĸļ士
    -0.68
    orthy
    -0.65
    hew
    -0.63
    çķ
    -0.62
    thren
    -0.62
    uncle
    -0.62
    iquette
    -0.61
    gey
    -0.61
    aiden
    -0.61
    POSITIVE LOGITS
     hostilities
    1.18
     bloodshed
    0.99
     homelessness
    0.81
     slavery
    0.79
     Violence
    0.78
     oppression
    0.77
     discrimination
    0.77
     experimentation
    0.76
     disbelief
    0.76
     paralysis
    0.76
    Activations Density 0.138%

    No Known Activations