INDEX

Explanations

references to paths in a programming context

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

The token "path"

np_acts-logits-general · gemini-2.0-flash

file paths and navigation

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bsen

-0.61

endente

-0.61

 reaſon

-0.61

 Becken

-0.60

 hänen

-0.59

 ſmall

-0.58

 Cellulose

-0.58

 Dirig

-0.57

 ſeveral

-0.57

 seated

-0.56

POSITIVE LOGITS

 Paths

0.96

 paths

0.94

 Path

0.91

 getPath

0.87

 PATH

0.86

paths

0.83

 path

0.80

WAY

0.78

ValueStyle

0.75

way

0.71

Activations Density 0.105%

references to paths in a programming context

The token "path"

file paths and navigation

No Comments

No Known Activations