Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 9527
    Prev
    Next
    INDEX
    Explanations

    phrases related to gathering, collecting, or accumulating things over time, both in a literal and abstract sense

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accumulation or gathering of resources or information

    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
    jah
    -0.75
    eller
    -0.74
    hift
    -0.72
    pper
    -0.71
    sey
    -0.70
    orthy
    -0.70
    overe
    -0.69
    pher
    -0.66
    nered
    -0.66
    psey
    -0.66
    POSITIVE LOGITS
     accum
    1.12
    ulative
    1.12
     accumulated
    1.11
     accumulation
    1.11
     accumulate
    1.10
     accumulating
    1.03
     piles
    0.92
    antine
    0.81
     amassed
    0.80
    rued
    0.79
    Activations Density 0.010%

    No Known Activations