INDEX

Explanations

expressions related to making choices or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 houſe

-0.74

 Monfieur

-0.72

 poffible

-0.71

 ſche

-0.69

 Conſ

-0.66

 paff

-0.64

 ſeveral

-0.63

 ")");

-0.63

AndEndTag

-0.62

/*

-0.60

POSITIVE LOGITS

 decided

0.85

 instead

0.82

 rather

0.77

 opted

0.76

 décidé

0.76

 решила

0.76

 opting

0.75

 решили

0.71

 chose

0.71

 choose

0.70

Activations Density 0.269%

expressions related to making choices or decisions

No Comments

No Known Activations