© 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. 4-RES-JB
    11. 10315
    Prev
    Next
    INDEX
    Explanations

    words related to decay or deterioration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to decay processes across various contexts

    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
    AMI
    -0.79
    ocular
    -0.76
    mn
    -0.76
    arov
    -0.73
    berman
    -0.73
    ilar
    -0.72
    idav
    -0.72
    MN
    -0.71
    isations
    -0.71
    itudes
    -0.71
    POSITIVE LOGITS
     decay
    1.22
    hyde
    0.98
     Decay
    0.83
     curve
    0.79
     decaying
    0.77
     poisoning
    0.75
    hower
    0.74
     curves
    0.72
    gradation
    0.71
     emitted
    0.70
    Activations Density 0.023%

    No Known Activations