INDEX

Explanations

phrases related to a specific entity called "Inter"

oai_token-act-pair · gpt-3.5-turbo

the term "Inter" in various contexts

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

EStream

-0.88

ggies

-0.86

\\\\\\\\

-0.84

ongs

-0.83

dylib

-0.78

 deaf

-0.77

unks

-0.72

 tremend

-0.71

avorite

-0.69

ggle

-0.68

POSITIVE LOGITS

ventions

1.01

mediate

0.98

continental

0.95

lude

0.95

medi

0.94

sectional

0.93

pol

0.91

section

0.90

mitt

0.88

Contin

0.85

Activations Density 0.009%

phrases related to a specific entity called "Inter"

the term "Inter" in various contexts

No Comments

No Known Activations