© 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. 1-RES-JB
    11. 16357
    Prev
    Next
    INDEX
    Explanations

    phrases related to commercial activity or products

    oai_token-act-pair · gpt-3.5-turbo

    terms related to commercial availability and economic implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aval
    -0.80
     Trace
    -0.72
     Laz
    -0.71
    oru
    -0.70
     Bog
    -0.70
     Io
    -0.69
    uyomi
    -0.68
    anan
    -0.65
     Myster
    -0.65
    stones
    -0.65
    POSITIVE LOGITS
     commercially
    1.07
    cially
    0.86
    ensable
    0.82
    wcs
    0.79
     RELE
    0.78
    atform
    0.77
    Ü
    0.77
    etically
    0.76
    ESE
    0.76
     speaking
    0.76
    Activations Density 0.012%

    No Known Activations