INDEX

Explanations

code-related terms and indicators for threading functions and error signals

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

 squire

-0.48

 Squire

-0.46

verk

-0.44

 verk

-0.44

 kosme

-0.41

gly

-0.41

 nautical

-0.41

 liter

-0.40

成的

-0.40

IBOutlet

-0.40

POSITIVE LOGITS

 Thread

1.04

 thread

0.90

Thread

0.89

pid

0.87

 Threads

0.81

 threads

0.81

pid

0.79

 THREAD

0.78

thread

0.77

ProcessEvent

0.76

Activations Density 0.538%

code-related terms and indicators for threading functions and error signals

No Comments

No Known Activations