INDEX

Explanations

arguments and discussions around errors and reasoning in logical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

orable

-0.44

ove

-0.44

assertAll

-0.43

indexOf

-0.43

onika

-0.43

 quoque

-0.42

Total

-0.42

 quai

-0.41

Reve

-0.41

 Total

-0.40

POSITIVE LOGITS

 minus

0.82

 without

0.82

 modified

0.79

 scaled

0.78

#+#

0.77

MessageTagHelper

0.73

 plus

0.73

 tweaked

0.71

 upside

0.70

WITHOUT

0.70

Activations Density 0.560%

arguments and discussions around errors and reasoning in logical contexts

No Comments

No Known Activations