INDEX

Explanations

phrases indicating quantity or intensity

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the term "so" to emphasize quantity or intensity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

theless

-0.65

works

-0.63

 Purg

-0.61

 Claims

-0.57

 referring

-0.56

 Peninsula

-0.55

 wiser

-0.54

 Mour

-0.54

 Heritage

-0.53

 Conrad

-0.53

POSITIVE LOGITS

oths

1.07

oooo

1.04

 many

0.98

 much

0.98

bs

0.96

apy

0.95

ooo

0.94

aps

0.93

bered

0.92

othes

0.89

Activations Density 0.063%

phrases indicating quantity or intensity

the repeated use of the term "so" to emphasize quantity or intensity

No Comments

No Known Activations