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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14699
    Prev
    Next
    INDEX
    Explanations

    terms related to development and advancement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to developmental processes and risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leans
    -0.84
    zzo
    -0.82
    ñ
    -0.82
    andra
    -0.80
    zzi
    -0.79
    Ń·
    -0.78
    pload
    -0.68
    hers
    -0.68
    htaking
    -0.67
    -+-+-+-+
    -0.67
    POSITIVE LOGITS
     developmental
    1.00
     disabilities
    0.81
     milestones
    0.76
     enrichment
    0.72
    onut
    0.70
    ities
    0.70
     evaluations
    0.70
     aspects
    0.69
     stages
    0.69
    oder
    0.68
    Activations Density 0.010%

    No Known Activations