INDEX

Explanations

references to specific terms or names

oai_token-act-pair · gpt-3.5-turbo

occurrences of the sequence "aa" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

enegger

-0.79

rified

-0.75

sticks

-0.71

 Canaver

-0.71

bourg

-0.68

cube

-0.67

ERAL

-0.67

OCD

-0.66

 Townsend

-0.66

ioned

-0.65

POSITIVE LOGITS

uthor

0.98

qqa

0.95

veland

0.91

ibaba

0.90

Ã±

0.86

aah

0.86

ccess

0.82

Ã°

0.82

ittle

0.82

ft

0.81

Activations Density 0.014%

references to specific terms or names

occurrences of the sequence "aa" in various contexts

No Comments

No Known Activations