INDEX

Explanations

words related to locations or places

oai_token-act-pair · gpt-3.5-turbo

the preposition "in" used frequently throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

peak

-0.80

ONEY

-0.75

DEV

-0.71

pent

-0.70

Ùħ

-0.70

ĸļ

-0.69

lain

-0.67

ngth

-0.65

HAEL

-0.65

wordpress

-0.65

POSITIVE LOGITS

strument

1.02

hib

0.93

iti

0.90

jured

0.83

hibit

0.82

clusive

0.82

vention

0.80

wards

0.80

jury

0.78

verting

0.78

Activations Density 0.032%

words related to locations or places

the preposition "in" used frequently throughout the text

No Comments

No Known Activations