INDEX

Explanations

phrases indicating the beginning of detailed information or a new statement

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "there was."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

arta

-0.79

otic

-0.74

mare

-0.68

obi

-0.67

ians

-0.66

ethy

-0.66

omorph

-0.64

asm

-0.62

lish

-0.61

oto

-0.61

POSITIVE LOGITS

 originally

0.74

hes

0.70

 formerly

0.69

 initially

0.69

 uproar

0.69

 reluct

0.68

 instrumental

0.66

ternity

0.66

 murm

0.66

 pandemonium

0.65

Activations Density 0.086%

phrases indicating the beginning of detailed information or a new statement

occurrences of the phrase "there was."

No Comments

No Known Activations