INDEX

Explanations

mentions of confidence and trust in various contexts

oai_token-act-pair · gpt-3.5-turbo

expressions of certainty or trust in various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

bard

-0.73

artist

-0.70

perse

-0.69

sites

-0.69

pmwiki

-0.66

cold

-0.66

Kin

-0.65

hid

-0.64

bye

-0.63

cise

-0.63

POSITIVE LOGITS

worthiness

1.19

 intervals

1.08

ially

0.93

 interval

0.80

 assurance

0.79

lessly

0.77

 confidence

0.77

worthy

0.76

 knowing

0.73

fulness

0.73

Activations Density 0.055%

mentions of confidence and trust in various contexts

expressions of certainty or trust in various subjects

No Comments

No Known Activations