INDEX

Explanations

words related to uncertainty

oai_token-act-pair · gpt-3.5-turbo

terms related to uncertainty and ambiguity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ovie

-0.91

endar

-0.85

olphins

-0.81

tha

-0.81

amina

-0.78

apsed

-0.78

ingo

-0.76

audi

-0.76

gdala

-0.75

zac

-0.74

POSITIVE LOGITS

 uncertainty

0.89

lessly

0.88

 shorth

0.83

 uncertainties

0.78

 doom

0.76

 surrounds

0.76

otiation

0.76

 fallout

0.73

 horizon

0.72

fully

0.72

Activations Density 0.019%

words related to uncertainty

terms related to uncertainty and ambiguity

No Comments

No Known Activations