© 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. 1-RES-JB
    11. 3687
    Prev
    Next
    INDEX
    Explanations

    names containing the string "ram"

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the word "ram."

    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
     proximity
    -0.68
    cius
    -0.68
     poss
    -0.67
     deed
    -0.66
     accord
    -0.65
     subordinate
    -0.64
     Occupations
    -0.63
     Parables
    -0.62
     readiness
    -0.62
     professions
    -0.61
    POSITIVE LOGITS
    ram
    1.35
    irez
    1.11
    rams
    1.03
    ming
    0.98
    aganda
    0.91
    matical
    0.91
    mers
    0.91
    med
    0.89
    abal
    0.88
    mus
    0.87
    Activations Density 0.007%

    No Known Activations