© 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. 4-RES-JB
    11. 6015
    Prev
    Next
    INDEX
    Explanations

    the word "Saf" with varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Saf" or related variations

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

    No Comments

    Negative Logits
    hunt
    -0.69
    hower
    -0.67
    icularly
    -0.65
     boiling
    -0.64
     Neptune
    -0.64
    ional
    -0.63
     chang
    -0.62
     Blessed
    -0.62
     Gall
    -0.62
     deaf
    -0.62
    POSITIVE LOGITS
    eties
    1.29
    eco
    1.04
    egu
    1.01
    saf
    0.96
    eway
    0.93
    avid
    0.88
    dar
    0.85
    aris
    0.83
    ecast
    0.82
    afi
    0.81
    Activations Density 0.007%

    No Known Activations