INDEX

Explanations

phrases related to panoramic views

oai_token-act-pair · gpt-3.5-turbo

references to pans 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

IELD

-0.74

éĽ

-0.70

æ©Ł

-0.70

é¾įå¥ĳå£«

-0.63

éĩ

-0.62

 Norn

-0.62

 Highlander

-0.60

 Gilmore

-0.59

=#

-0.58

ERE

-0.57

POSITIVE LOGITS

orama

1.11

pan

0.90

handler

0.89

asonic

0.86

eful

0.85

omaly

0.84

thood

0.84

ophon

0.84

acea

0.84

artisan

0.83

Activations Density 0.006%

phrases related to panoramic views

references to pans in various contexts

No Comments

No Known Activations