INDEX

Explanations

dates related to the year 2015

oai_token-act-pair · gpt-3.5-turbo

occurrences of the year 2015

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

agic

-0.72

 cumbers

-0.71

phia

-0.68

oxin

-0.66

FACE

-0.64

ymm

-0.62

ess

-0.62

 recip

-0.62

ocom

-0.61

sym

-0.60

POSITIVE LOGITS

å¹

0.89

0.84

rak

0.75

#$

0.72

 Brav

0.72

 onwards

0.71

âĢ²

0.71

gress

0.70

furt

0.69

thal

0.69

Activations Density 0.034%

dates related to the year 2015

occurrences of the year 2015

No Comments

No Known Activations