© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19057
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions involving law enforcement or authority, such as "encompassing" or "trespassing"

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of trespassing and infringement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fixed
    -0.71
     Sponsor
    -0.65
     parent
    -0.64
     McDonnell
    -0.63
     fal
    -0.63
    Ùİ
    -0.61
     eleg
    -0.61
     fid
    -0.61
     inherit
    -0.60
     Fib
    -0.60
    POSITIVE LOGITS
    assing
    4.43
    assed
    3.42
    asses
    2.23
    assment
    1.89
    ass
    1.69
    asser
    1.33
    ASS
    1.33
    assy
    1.20
    asing
    1.12
    assian
    1.11
    Activations Density 0.011%

    No Known Activations