INDEX

Explanations

mentions of the word "water"

oai_token-act-pair · gpt-3.5-turbo

terms related to water or water-related contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ured

-0.80

urers

-0.69

ures

-0.66

_>

-0.64

Disk

-0.63

uration

-0.62

 edible

-0.60

 diabetic

-0.60

 fung

-0.60

berman

-0.59

POSITIVE LOGITS

pillar

1.08

IAL

0.96

apy

0.91

ickson

0.90

idon

0.90

geist

0.84

pill

0.82

eor

0.80

dam

0.79

ater

0.78

Activations Density 0.025%

mentions of the word "water"

terms related to water or water-related contexts

No Comments

No Known Activations