INDEX

Explanations

instances of the word "turn" and its variations in different contexts

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

 ſche

-0.79

 pleaſure

-0.79

IntoConstraints

-0.71

 niyang

-0.70

 leſs

-0.69

 houſe

-0.66

hasMoreElements

-0.66

 ainfi

-0.66

 doubtnut

-0.65

 richi

-0.65

POSITIVE LOGITS

 Turn

0.85

arounds

0.82

Turn

0.82

 TURN

0.81

TURN

0.78

 turns

0.78

 around

0.77

Turning

0.77

 turn

0.76

 upside

0.75

Activations Density 0.075%

instances of the word "turn" and its variations in different contexts

No Comments

No Known Activations