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. 3777
    Prev
    Next
    INDEX
    Explanations

    phrases related to commitment or adherence to a plan

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to adherence or consistency

    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
    ELF
    -0.78
    ocaust
    -0.74
    ģ«
    -0.72
    apest
    -0.72
    Ĥİ
    -0.71
    lav
    -0.68
    ´
    -0.68
    İ
    -0.67
    Tu
    -0.67
     Dhabi
    -0.66
    POSITIVE LOGITS
    itiveness
    0.84
    thin
    0.74
    ciating
    0.74
     toes
    0.69
     sticks
    0.68
     Puzzles
    0.68
     Clicker
    0.66
    shore
    0.66
     stick
    0.66
     bang
    0.65
    Activations Density 0.055%

    No Known Activations