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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 352
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial figures and business outcomes

    oai_token-act-pair · gpt-3.5-turbo

    financial metrics and projections related to revenue and taxation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Exhibition
    -0.49
     Sketch
    -0.48
    gha
    -0.48
     Honour
    -0.45
     Jol
    -0.45
     Serpent
    -0.44
    uder
    -0.42
    idth
    -0.42
     Resurrection
    -0.41
     Sin
    -0.41
    POSITIVE LOGITS
    etheless
    0.72
    NetMessage
    0.65
    conom
    0.64
    Ĥİ
    0.59
    ĵĺ
    0.59
    natureconservancy
    0.58
     disproportionately
    0.56
    ibaba
    0.55
     unfavorable
    0.55
     disproportion
    0.53
    Activations Density 6.177%

    No Known Activations