INDEX

Explanations

phrases related to trustworthiness and reliability

oai_token-act-pair · gpt-3.5-turbo

expressions related to trust and trustworthiness

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nesota

-0.82

plex

-0.77

theme

-0.77

owitz

-0.77

atre

-0.76

neapolis

-0.74

vention

-0.72

burg

-0.71

ozo

-0.70

alities

-0.69

POSITIVE LOGITS

worthiness

1.06

 trusted

0.98

 confid

0.93

 trustworthy

0.86

lessly

0.80

iliate

0.77

 intermediary

0.77

 intervals

0.75

rius

0.73

 marg

0.72

Activations Density 0.010%

phrases related to trustworthiness and reliability

expressions related to trust and trustworthiness

No Comments

No Known Activations