INDEX

Explanations

programming-related terms and syntax

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 estekak

-0.63

ioctl

-0.48

isor

-0.47

 Manner

-0.45

srv

-0.44

 resourceCulture

-0.44

obs

-0.43

 Durand

-0.43

 Verr

-0.42

 vice

-0.42

POSITIVE LOGITS

 stack

0.74

ObjectContext

0.68

 frame

0.66

 frames

0.65

frame

0.62

 Frames

0.61

stack

0.61

 locals

0.59

Frame

0.59

 Frame

0.58

Activations Density 0.396%

programming-related terms and syntax

No Comments

No Known Activations