INDEX

Explanations

the word "Sometimes"

oai_token-act-pair · gpt-3.5-turbo

the repetition of the word "Sometimes."

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

zag

-0.81

eting

-0.79

yet

-0.79

shi

-0.78

mson

-0.73

iants

-0.72

ye

-0.72

gur

-0.71

ryan

-0.70

band

-0.70

POSITIVE LOGITS

entimes

1.05

theless

1.04

pmwiki

1.02

etheless

0.99

 overlooked

0.87

 glimps

0.79

 mistaken

0.77

 unsus

0.76

interstitial

0.75

 misunderstood

0.75

Activations Density 0.027%

the word "Sometimes"

the repetition of the word "Sometimes."

No Comments

No Known Activations