INDEX

Explanations

mentions of changes or transformations in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "changed" that indicate transformation or alteration in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

amina

-0.93

ç«

-0.81

mination

-0.76

 DRAGON

-0.72

APH

-0.70

stra

-0.67

alty

-0.66

á

-0.66

ILA

-0.64

onz

-0.64

POSITIVE LOGITS

ĸļ

1.12

 destro

0.78

 hijacked

0.77

changed

0.77

 radically

0.75

ulkan

0.75

xual

0.74

 effected

0.74

rawdownloadcloneembedreportprint

0.73

 drastically

0.72

Activations Density 0.015%

mentions of changes or transformations in various contexts

instances of the word "changed" that indicate transformation or alteration in various contexts

No Comments

No Known Activations