INDEX

Explanations

phrases related to reasonable or logical thinking

oai_token-act-pair · gpt-3.5-turbo

references to rationality or common sense in discussions about people and their behaviors

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Reloaded

-0.69

 Anniversary

-0.66

 disappearance

-0.65

 Regions

-0.62

 Territories

-0.61

 Promise

-0.60

apeake

-0.60

 Siege

-0.60

 rehearsal

-0.59

forestation

-0.59

POSITIVE LOGITS

 inclined

0.85

think

0.83

kie

0.80

ellectual

0.80

thinking

0.79

tarian

0.78

iuses

0.78

ascript

0.77

 instinctively

0.77

enance

0.77

Activations Density 0.377%

phrases related to reasonable or logical thinking

references to rationality or common sense in discussions about people and their behaviors

No Comments

No Known Activations