© 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. 2-RES-JB
    11. 23917
    Prev
    Next
    INDEX
    Explanations

    words related to the city "Dhaka"

    oai_token-act-pair · gpt-3.5-turbo

    references to places or terminology related to Dhaka and DHCP

    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
    éĹĺ
    -0.94
    swick
    -0.82
    */(
    -0.78
    PsyNetMessage
    -0.76
    NetMessage
    -0.76
    eering
    -0.75
    secut
    -0.74
     referrals
    -0.73
     therapy
    -0.71
    izations
    -0.70
    POSITIVE LOGITS
     Dh
    1.22
    awan
    0.99
    onest
    0.98
    arm
    0.94
    ancing
    0.93
    abal
    0.92
    aval
    0.89
    uran
    0.89
    arma
    0.88
    ahah
    0.88
    Activations Density 0.005%

    No Known Activations