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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4575
    Prev
    Next
    INDEX
    Explanations

    words related to nicknames

    oai_token-act-pair · gpt-3.5-turbo

    terms related to names and nicknames

    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
    ÂŃ
    -0.70
    rane
    -0.66
    il
    -0.65
     conver
    -0.62
    viol
    -0.60
    forces
    -0.59
     determin
    -0.58
    aris
    -0.58
    Far
    -0.58
    ocent
    -0.57
    POSITIVE LOGITS
     nickname
    3.90
     moniker
    2.47
     nick
    2.13
     pseudonym
    1.90
     surname
    1.83
     nicknamed
    1.74
     initials
    1.69
     name
    1.59
     acronym
    1.58
     abbre
    1.43
    Activations Density 0.021%

    No Known Activations