© 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. 18549
    Prev
    Next
    INDEX
    Explanations

    phrases related to making an effort or doing what one can

    oai_token-act-pair · gpt-3.5-turbo

    expressions of capability and effort

    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
     Grav
    -0.59
     Orbital
    -0.59
     Consortium
    -0.58
     Nom
    -0.58
     Than
    -0.57
     Abram
    -0.57
     Dri
    -0.57
     Kappa
    -0.57
    head
    -0.56
     Bacon
    -0.56
    POSITIVE LOGITS
    've
    0.88
    ngth
    0.86
    're
    0.82
    needed
    0.78
     encount
    0.78
     own
    0.77
     deems
    0.77
     reasonably
    0.75
     feas
    0.74
    iple
    0.73
    Activations Density 0.228%

    No Known Activations