© 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. 8-RES-JB
    11. 6251
    Prev
    Next
    INDEX
    Explanations

    stock symbols

    oai_token-act-pair · gpt-3.5-turbo

    financial entities and stock market references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    giene
    -0.76
    ilege
    -0.71
     Cage
    -0.70
     passage
    -0.69
     Feast
    -0.66
     infiltration
    -0.66
     ghetto
    -0.66
     Chomsky
    -0.65
     Pole
    -0.64
     Temper
    -0.64
    POSITIVE LOGITS
    NYSE
    1.61
    DAQ
    1.27
    daq
    1.11
     Holdings
    1.07
    AX
    0.99
    NAS
    0.98
     subsidiaries
    0.96
    MX
    0.95
    BN
    0.93
    ZX
    0.92
    Activations Density 0.184%

    No Known Activations