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. 9869
    Prev
    Next
    INDEX
    Explanations

    comparisons or similarities between different subjects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "too," indicating a sense of addition or emphasis in statements

    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
     caster
    -0.70
     Versus
    -0.69
     newsp
    -0.60
     ONLY
    -0.58
    elf
    -0.58
     technician
    -0.56
     Accountability
    -0.56
     millisec
    -0.56
     mindset
    -0.54
    earth
    -0.54
    POSITIVE LOGITS
    vous
    0.83
     sidx
    0.74
    ̶
    0.72
    otton
    0.72
    esson
    0.71
    ettings
    0.71
    uld
    0.70
    LET
    0.70
    ilon
    0.69
    endiary
    0.68
    Activations Density 0.098%

    No Known Activations