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. 4646
    Prev
    Next
    INDEX
    Explanations

    verbs related to releasing or causing something powerful or intense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unleash" and its variations

    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
     Represent
    -0.72
    ©¶æ
    -0.71
    aque
    -0.71
    ental
    -0.70
    iasis
    -0.70
    iop
    -0.70
    ovember
    -0.69
    sem
    -0.68
    atem
    -0.64
     Advance
    -0.64
    POSITIVE LOGITS
     havoc
    1.00
     unleashed
    0.96
     unle
    0.87
    ãĥ¤
    0.82
     mayhem
    0.80
     DRAG
    0.79
    UGE
    0.78
     unleash
    0.75
    ãĤ¸
    0.73
    doors
    0.72
    Activations Density 0.032%

    No Known Activations