© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12464
    Prev
    Next
    INDEX
    Explanations

    words related to levels of intensity or satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating moderation or the degree of intensity

    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
    hyde
    -0.82
    iens
    -0.80
    inates
    -0.74
    inators
    -0.73
    sing
    -0.72
    idia
    -0.70
    inatory
    -0.66
    otte
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.65
    enance
    -0.65
    POSITIVE LOGITS
     risky
    0.77
     expensive
    0.77
     much
    0.76
     len
    0.73
     costly
    0.72
     severe
    0.69
     busy
    0.69
     close
    0.68
     detectable
    0.68
     noticeable
    0.68
    Activations Density 0.030%

    No Known Activations