© 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. 4-RES-JB
    11. 88
    Prev
    Next
    INDEX
    Explanations

    phrases related to probabilities or chances

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating probabilities or chances of events occurring

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

    No Comments

    Negative Logits
     ILCS
    -0.87
    hesis
    -0.83
    arch
    -0.78
    minus
    -0.76
    Reviewer
    -0.76
    entric
    -0.73
    heses
    -0.71
    uristic
    -0.69
    idelines
    -0.69
    lass
    -0.68
    POSITIVE LOGITS
     obtaining
    0.83
     impending
    0.81
     staying
    0.76
     locating
    0.74
     getting
    0.72
     retribution
    0.72
     encountering
    0.72
     tomorrow
    0.71
     registering
    0.71
     acquiring
    0.71
    Activations Density 0.150%

    No Known Activations