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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8996
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "falling into" something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "fall into"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    der
    -0.76
    killer
    -0.74
    conn
    -0.70
    cies
    -0.68
    warning
    -0.67
     indu
    -0.66
    nea
    -0.65
    die
    -0.65
     DeL
    -0.64
    redo
    -0.63
    POSITIVE LOGITS
     adulthood
    0.77
    hift
    0.73
    adow
    0.71
    opol
    0.71
    obin
    0.69
    izoph
    0.69
    displayText
    0.69
     accordance
    0.68
     conformity
    0.68
    agos
    0.68
    Activations Density 0.037%

    No Known Activations