© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 22589
    Prev
    Next
    INDEX
    Explanations

    instances relating to landing or crashing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "landing" and its variations within a context related to physical arrival or placement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    die
    -0.72
    ework
    -0.70
    vernment
    -0.68
    inki
    -0.65
    uv
    -0.65
     overload
    -0.65
    éĹĺ
    -0.64
    acity
    -0.64
    etts
    -0.63
    é¾įå¥ij士
    -0.62
    POSITIVE LOGITS
    plane
    0.89
     squarely
    0.81
    planes
    0.77
    locked
    0.77
    prises
    0.71
    rences
    0.70
    mass
    0.69
     awkwardly
    0.69
    lock
    0.69
     safely
    0.69
    Activations Density 0.038%

    No Known Activations