INDEX

Explanations

phrases related to distance or extent

oai_token-act-pair · gpt-3.5-turbo

references to progress or distance traveled

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

variable

-0.70

Ò

-0.67

é¾

-0.66

çļ

-0.66

advertisement

-0.65

Buzz

-0.65

-0.62

ciating

-0.61

 Parenthood

-0.61

OTOS

-0.60

POSITIVE LOGITS

 tread

0.82

eele

0.79

 encro

0.78

 toward

0.77

 slopes

0.75

 towards

0.73

 distances

0.73

 pend

0.71

 descent

0.71

reaching

0.71

Activations Density 0.158%

phrases related to distance or extent

references to progress or distance traveled

No Comments

No Known Activations