© 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. 9-RES-JB
    11. 3688
    Prev
    Next
    INDEX
    Explanations

    geographic locations and descriptive geographical terms

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exhib
    -0.74
     rookies
    -0.72
     rookie
    -0.70
     workplace
    -0.69
     personalized
    -0.69
     warranted
    -0.68
    ARCH
    -0.67
    appropriate
    -0.66
     innovate
    -0.66
    STEM
    -0.66
    POSITIVE LOGITS
     southwest
    1.21
     northwest
    1.20
     northeast
    1.18
     southwestern
    1.14
     northern
    1.13
     northwestern
    1.12
    outhern
    1.12
     east
    1.10
     northeastern
    1.09
     north
    1.08
    Activations Density 0.457%

    No Known Activations