INDEX

Explanations

phrases related to tasks or actions that involve effort or a process

oai_token-act-pair · gpt-3.5-turbo

references to established practices or metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

adan

-0.78

 Tycoon

-0.78

adra

-0.76

utra

-0.71

 Simulator

-0.66

amaz

-0.64

 Shake

-0.64

yip

-0.63

assium

-0.62

apo

-0.61

POSITIVE LOGITS

paren

0.88

own

0.83

ancer

0.80

dit

0.78

escription

0.78

gew

0.70

icular

0.70

iatrics

0.70

ouble

0.70

irect

0.68

Activations Density 0.336%

phrases related to tasks or actions that involve effort or a process

references to established practices or metrics

No Comments

No Known Activations