© 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. 1-RES-JB
    11. 16902
    Prev
    Next
    INDEX
    Explanations

    languages related to moral purity and innocence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to purity and innocence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kson
    -0.84
    Īè
    -0.72
    ãĤī
    -0.70
    bers
    -0.68
     behav
    -0.67
    IRD
    -0.67
    iverse
    -0.65
    acter
    -0.64
    sf
    -0.63
    sg
    -0.63
    POSITIVE LOGITS
    fulness
    1.06
     purity
    0.99
    cius
    0.94
    iness
    0.92
    lessness
    0.90
    urity
    0.90
    ldom
    0.89
     innocence
    0.86
    acies
    0.86
    urities
    0.79
    Activations Density 0.021%

    No Known Activations