INDEX

Explanations

phrases related to beliefs, assumptions, and theories

oai_token-act-pair · gpt-3.5-turbo

words related to assumptions and beliefs

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

Interstitial

-0.83

sung

-0.75

waters

-0.71

odes

-0.70

thumbnails

-0.69

ateurs

-0.67

oho

-0.65

avid

-0.65

umen

-0.63

HCR

-0.63

POSITIVE LOGITS

 assumptions

1.00

 assumption

0.92

 underpin

0.80

staking

0.75

 assumes

0.73

eers

0.68

 presupp

0.67

 biases

0.66

 premise

0.66

arily

0.65

Activations Density 0.015%

phrases related to beliefs, assumptions, and theories

words related to assumptions and beliefs

No Comments

No Known Activations