INDEX

Explanations

instances of the word "entry"

oai_token-act-pair · gpt-3.5-turbo

references to "entry" in various contexts, indicating different levels and situations

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

 Carth

-0.69

 opio

-0.68

 tremend

-0.64

ascus

-0.64

illac

-0.62

gans

-0.62

yth

-0.62

awar

-0.61

 Parables

-0.61

 Balanced

-0.61

POSITIVE LOGITS

apore

0.88

 entry

0.85

prise

0.81

ways

0.80

tain

0.77

prising

0.75

entry

0.75

door

0.75

lude

0.74

tainment

0.74

Activations Density 0.022%

instances of the word "entry"

references to "entry" in various contexts, indicating different levels and situations

No Comments

No Known Activations