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. 10-RES-JB
    6. 19920
    Prev
    Next
    INDEX
    Explanations

    phrases related to feedback or response to statements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of appreciation and support for unity and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĺ
    -0.81
     disappearance
    -0.76
     ruining
    -0.76
     revenge
    -0.75
    livion
    -0.74
     thief
    -0.71
     vanish
    -0.71
    digy
    -0.71
     ruined
    -0.70
    die
    -0.70
    POSITIVE LOGITS
     bipartisan
    1.29
     briefed
    1.13
     constructive
    1.13
     discussions
    1.12
     consultations
    1.12
     deliberations
    1.11
     thoughtful
    1.05
     consultation
    1.03
     deliber
    1.00
     counsel
    0.99
    Activations Density 0.789%

    No Known Activations