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. 7-RES-JB
    6. 22783
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to excitement, anticipation, or promotion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to excitement and public interest, particularly the word "buzz."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.68
    ãģ®å
    -0.67
    tein
    -0.65
     Equality
    -0.65
     Refuge
    -0.64
    abama
    -0.61
     Yard
    -0.59
     hostages
    -0.58
     diam
    -0.57
     loans
    -0.57
    POSITIVE LOGITS
    INESS
    1.06
     buzz
    0.98
    waves
    0.96
    saw
    0.93
    iest
    0.89
    wave
    0.88
    worthy
    0.87
    phrase
    0.87
    iness
    0.87
    bub
    0.83
    Activations Density 0.040%

    No Known Activations