INDEX

Explanations

ways or solutions to a problem

oai_token-act-pair · gpt-3.5-turbo

phrases indicating methods or solutions to achieve something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

usters

-0.79

 livest

-0.77

ewitness

-0.77

anamo

-0.72

inately

-0.71

uster

-0.71

hemat

-0.71

etheus

-0.70

grave

-0.69

eatures

-0.68

POSITIVE LOGITS

finding

0.92

fare

0.91

ward

0.89

point

0.88

forward

0.85

 somew

0.76

 backdoor

0.71

 forward

0.70

 workaround

0.67

lay

0.66

Activations Density 0.038%

ways or solutions to a problem

phrases indicating methods or solutions to achieve something

No Comments

No Known Activations