INDEX

Explanations

references to indirect effects in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Anſ

-1.03

ſelves

-1.02

Efq

-0.97

Geplaatst

-0.97

 Theſe

-0.94

ſelf

-0.92

$_"

-0.92

 Reſ

-0.91

 Houſe

-0.91

 ſever

-0.91

POSITIVE LOGITS

 weakness

0.73

weak

0.70

 weak

0.62

 weaknesses

0.57

 Weak

0.54

WEAK

0.53

 Weakness

0.53

Exists

0.53

Weak

0.52

0.51

Activations Density 0.068%

references to indirect effects in various contexts

No Comments

No Known Activations