© 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. 10-RES-JB
    11. 9317
    Prev
    Next
    INDEX
    Explanations

    references to garbage, specifically dumpsters or the act of dumping items

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "dump" in various contexts, particularly related to waste or undesirable situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HCR
    -0.79
    iam
    -0.77
     obser
    -0.75
    éĸ
    -0.67
    akers
    -0.67
    ghai
    -0.66
     Realms
    -0.65
    ews
    -0.65
    emis
    -0.65
    iae
    -0.63
    POSITIVE LOGITS
    ster
    1.29
    sters
    1.15
     dumps
    0.97
    dump
    0.94
    bish
    0.82
     cans
    0.81
     landfill
    0.80
     dump
    0.80
     overboard
    0.77
     heap
    0.76
    Activations Density 0.034%

    No Known Activations