© 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. 1-RES-JB
    11. 16805
    Prev
    Next
    INDEX
    Explanations

    instances where something is being offered

    oai_token-act-pair · gpt-3.5-turbo

    the word "offered" and its variations

    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
     habit
    -0.64
    cas
    -0.63
    isol
    -0.62
    odore
    -0.62
    cling
    -0.61
    brance
    -0.61
    ritical
    -0.61
    lat
    -0.60
     genesis
    -0.59
    riot
    -0.59
    POSITIVE LOGITS
     offered
    1.06
     offers
    0.91
    ĸļ
    0.89
     offering
    0.86
     offerings
    0.83
     condolences
    0.77
    pta
    0.76
     showc
    0.72
     offer
    0.72
     unavailable
    0.71
    Activations Density 0.014%

    No Known Activations