INDEX

Explanations

acronyms or abbreviations following the pattern "DP #" where # is a number

oai_token-act-pair · gpt-3.5-turbo

references to specific data points or metrics in reports

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

glers

-0.84

itud

-0.80

ton

-0.75

mares

-0.75

ãĤ¤ãĥĪ

-0.74

swick

-0.74

umn

-0.73

 Merlin

-0.72

combe

-0.70

taboola

-0.70

POSITIVE LOGITS

rint

1.14

olicy

1.01

onent

0.96

ixel

0.95

ressed

0.93

arent

0.88

IR

0.83

etition

0.82

osition

0.82

ascal

0.79

Activations Density 0.009%

acronyms or abbreviations following the pattern "DP #" where # is a number

references to specific data points or metrics in reports

No Comments

No Known Activations