INDEX

Explanations

possibilities or uncertainties about future actions or events

oai_token-act-pair · gpt-3.5-turbo

probabilistic statements and predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Truth

-0.73

dam

-0.72

 Truth

-0.72

ocrates

-0.70

heid

-0.65

htaking

-0.65

rity

-0.65

rav

-0.63

raint

-0.61

washer

-0.61

POSITIVE LOGITS

 sooner

0.98

 relocate

0.93

 postpone

0.87

 reintrodu

0.86

 postp

0.85

 revisit

0.84

 decide

0.83

 renegoti

0.83

 revert

0.82

 reconsider

0.82

Activations Density 0.477%

possibilities or uncertainties about future actions or events

probabilistic statements and predictions

No Comments

No Known Activations