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. 13345
    Prev
    Next
    INDEX
    Explanations

    phrases with the specific word "deprived" followed by other descriptive terms like "of sleep" or "endlessly confronted by the deaths of"

    oai_token-act-pair · gpt-3.5-turbo

    the character "ó" in various contexts

    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
    orial
    -0.76
    achine
    -0.75
    ulse
    -0.65
    pread
    -0.65
    creen
    -0.62
    ensable
    -0.61
    aunted
    -0.61
    othal
    -0.61
     CST
    -0.61
    acle
    -0.61
    POSITIVE LOGITS
    rien
    1.10
    ÃįÃį
    0.88
    vez
    0.85
    ð
    0.84
    vernment
    0.83
    rez
    0.81
    ng
    0.81
    Ãį
    0.80
    ó
    0.80
    ndum
    0.80
    Activations Density 0.008%

    No Known Activations