© 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. 8-RES-JB
    11. 8976
    Prev
    Next
    INDEX
    Explanations

    mentions of occurrences that are triggered or happen when certain conditions are met

    oai_token-act-pair · gpt-3.5-turbo

    actions and consequences related to rules, penalties, and events in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeb
    -0.69
    ©¶æ¥µ
    -0.69
    çīĪ
    -0.66
     srfAttach
    -0.64
     accordingly
    -0.58
     Moroc
    -0.58
     Indra
    -0.57
    never
    -0.56
     Neh
    -0.56
     Establishment
    -0.55
    POSITIVE LOGITS
    pires
    0.81
     unexpectedly
    0.70
     fails
    0.68
     suddenly
    0.67
     somebody
    0.65
     wrong
    0.65
     or
    0.64
     enters
    0.63
    cery
    0.61
    uberty
    0.60
    Activations Density 0.641%

    No Known Activations