INDEX

Explanations

variations of the phrase "I don't."

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "I don't"

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

 Dise

-0.75

 VERS

-0.70

 afore

-0.70

sighted

-0.68

DOC

-0.67

ategory

-0.66

milo

-0.66

 Vision

-0.64

 Ability

-0.64

cised

-0.63

POSITIVE LOGITS

't

1.57

uts

0.96

kie

0.88

nell

0.84

nie

0.82

ned

0.82

ÃŃ

0.80

ning

0.77

ates

0.76

ct

0.75

Activations Density 0.057%

variations of the phrase "I don't."

instances of the phrase "I don't"

No Comments

No Known Activations