Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 15821
    Prev
    Next
    INDEX
    Explanations

    explicit uses of the word "so" as a connector or intensifier

    oai_token-act-pair · gpt-3.5-turbo

    the word "so" used as an intensifier or modifier in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glances
    -0.68
    gie
    -0.65
    rals
    -0.57
    Got
    -0.55
    theless
    -0.55
     presentation
    -0.54
     fixme
    -0.53
    DERR
    -0.53
     pinch
    -0.53
    amac
    -0.52
    POSITIVE LOGITS
    bered
    1.07
    oths
    1.06
    oner
    0.96
    othes
    0.94
     far
    0.91
    arer
    0.89
    iled
    0.88
    othe
    0.87
    apy
    0.83
    vere
    0.80
    Activations Density 0.106%

    No Known Activations