© 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. 2-RES-JB
    11. 12291
    Prev
    Next
    INDEX
    Explanations

    words related to collaborations or partnerships as indicated by terms such as "co-founder," "co-host," and "co-creator."

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to collaboration and teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     backlog
    -0.73
    ¥µ
    -0.69
     Intermediate
    -0.66
     impending
    -0.65
     peninsula
    -0.63
     cruise
    -0.62
     moot
    -0.62
    ovych
    -0.62
     PRES
    -0.60
     contem
    -0.60
    POSITIVE LOGITS
    rency
    1.01
    achment
    0.75
    earcher
    0.73
    gress
    0.72
    adia
    0.71
    alties
    0.71
    uay
    0.70
    erto
    0.70
    usting
    0.70
    interstitial
    0.69
    Activations Density 0.135%

    No Known Activations