INDEX

Explanations

words related to geographical locations, specifically the river "Tiber"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "iber."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ĸļ

-0.76

 pity

-0.69

urations

-0.66

atche

-0.64

ath

-0.62

 Mehran

-0.61

isters

-0.61

¬¼

-0.60

erness

-0.59

Ta

-0.59

POSITIVE LOGITS

tarian

1.07

glass

1.00

tarians

0.99

iber

0.92

ulent

0.85

glas

0.84

gence

0.78

dict

0.77

gins

0.77

nation

0.76

Activations Density 0.012%

words related to geographical locations, specifically the river "Tiber"

occurrences of the substring "iber."

No Comments

No Known Activations