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. 22485
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progression, change, or development

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of "coming about" or "arriving at" a situation or condition

    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
    livious
    -0.66
     hobbies
    -0.60
    nesota
    -0.60
     Auckland
    -0.58
    tein
    -0.58
    laughs
    -0.58
    friend
    -0.58
     Activities
    -0.57
    llan
    -0.56
     motives
    -0.56
    POSITIVE LOGITS
     fruition
    0.80
    UE
    0.77
     blows
    0.75
     undone
    0.72
    hest
    0.71
    itol
    0.66
    asse
    0.65
    ë
    0.65
    ãĤ¼
    0.65
    uer
    0.64
    Activations Density 0.120%

    No Known Activations