© 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. 16900
    Prev
    Next
    INDEX
    Explanations

    locations or directions where someone or something has moved

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "moved" and related phrases indicating relocation

    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
    TEXT
    -0.77
    lime
    -0.71
    nia
    -0.66
    rous
    -0.66
    ught
    -0.65
    cture
    -0.65
    aptic
    -0.64
    otine
    -0.64
    ze
    -0.62
    MET
    -0.60
    POSITIVE LOGITS
     abroad
    0.86
     away
    0.82
     into
    0.81
     permanently
    0.80
    igrated
    0.80
     home
    0.78
    away
    0.75
     downstairs
    0.75
     indoors
    0.75
     apartments
    0.74
    Activations Density 0.101%

    No Known Activations