© 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. 6832
    Prev
    Next
    INDEX
    Explanations

    names or references related to "Mos" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the entity "Mos" or related names

    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
    istics
    -0.78
    istically
    -0.72
    DragonMagazine
    -0.69
    sburgh
    -0.67
     Thumbnails
    -0.67
    istical
    -0.67
    OWN
    -0.66
     Takeru
    -0.65
     Immunity
    -0.64
     Rite
    -0.63
    POSITIVE LOGITS
    aic
    1.06
    sey
    1.04
    ques
    1.02
    quet
    1.02
    daq
    1.01
    quit
    0.99
    chal
    0.98
    cone
    0.98
    cot
    0.94
    cos
    0.94
    Activations Density 0.025%

    No Known Activations