INDEX

Explanations

German words and locations

oai_token-act-pair · gpt-3.5-turbo

repeated patterns or sequences of characters within words

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

theless

-0.74

enhagen

-0.73

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.69

 prosecut

-0.67

PDATE

-0.67

avorite

-0.66

Downloadha

-0.65

é¾įå

-0.64

 GOODMAN

-0.64

minecraft

-0.63

POSITIVE LOGITS

anooga

0.80

lain

0.77

×Ļ

0.77

obos

0.74

jee

0.73

hov

0.73

acter

0.71

ynski

0.69

 Lumpur

0.68

aten

0.68

Activations Density 0.224%

German words and locations

repeated patterns or sequences of characters within words

No Comments

No Known Activations