© 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. 0-RES-JB
    11. 22316
    Prev
    Next
    INDEX
    Explanations

    details related to specific examples or instances within larger categories or contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that list examples or instances of items or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     someone
    -0.66
     rec
    -0.63
     college
    -0.61
     mom
    -0.61
     daughter
    -0.61
     wheels
    -0.60
     states
    -0.60
     version
    -0.60
     rack
    -0.60
     wheel
    -0.60
    POSITIVE LOGITS
    including
    3.41
    excluding
    2.16
    except
    1.97
     Including
    1.88
    especially
    1.86
    particularly
    1.79
    includes
    1.76
    whether
    1.60
    such
    1.60
    both
    1.56
    Activations Density 0.014%

    No Known Activations