INDEX

Explanations

phrases related to success or achieving a goal

oai_token-act-pair · gpt-3.5-turbo

instances of the word "hit" 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

pires

-0.87

ç«

-0.72

inent

-0.71

agin

-0.68

æĢ

-0.67

æ©Ł

-0.66

orld

-0.66

otive

-0.64

pite

-0.62

cia

-0.62

POSITIVE LOGITS

ched

1.08

hit

0.82

achi

0.82

tle

0.80

boxes

0.78

ches

0.77

ted

0.73

 puberty

0.73

arro

0.71

gerald

0.71

Activations Density 0.027%

phrases related to success or achieving a goal

instances of the word "hit" in various contexts

No Comments

No Known Activations