INDEX

Explanations

instances of honey and jars, particularly in a context that suggests measurement or quantification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 itſelf

-0.86

 Monfieur

-0.86

 Jefus

-0.85

 houſe

-0.79

 purpoſe

-0.76

 ſtand

-0.76

 ſta

-0.76

 iſt

-0.76

 raiſ

-0.75

 ſeveral

-0.75

POSITIVE LOGITS

 lenker

0.58

gi

0.48

sch

0.44

altor

0.44

 extra

0.43

thus

0.43

 Schroeder

0.42

bu

0.41

Activations Density 0.027%

instances of honey and jars, particularly in a context that suggests measurement or quantification

No Comments

No Known Activations