© 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. 10-RES-JB
    11. 2776
    Prev
    Next
    INDEX
    Explanations

    restrictions, rules, and eligibility criteria

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating conditions or eligibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sophistication
    -0.80
     Subtle
    -0.77
    ciating
    -0.74
     Extrem
    -0.73
    PsyNetMessage
    -0.72
    rawdownloadcloneembedreportprint
    -0.72
     Commando
    -0.70
    warm
    -0.69
     srfAttach
    -0.69
    Untitled
    -0.65
    POSITIVE LOGITS
     eligible
    1.50
     exempted
    1.50
     excluded
    1.43
     exempt
    1.42
     disqualified
    1.41
     ineligible
    1.39
     barred
    1.38
     allowed
    1.38
     permitted
    1.34
     counted
    1.33
    Activations Density 0.209%

    No Known Activations