INDEX

Explanations

phrases mentioning a cost or negative consequence that needs to be paid

oai_token-act-pair · gpt-3.5-turbo

references to the concept of cost or payment, particularly regarding societal implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

riter

-0.92

dayName

-0.90

ahime

-0.86

utenberg

-0.83

[|

-0.81

intend

-0.81

Champ

-0.80

uggest

-0.80

ovy

-0.79

itialized

-0.79

POSITIVE LOGITS

 inflicted

0.91

 sacrifice

0.86

 toll

0.86

 incurred

0.85

 casualties

0.84

 dearly

0.84

 defeat

0.79

 suffered

0.79

 spared

0.79

 sacrifices

0.77

Activations Density 0.094%

phrases mentioning a cost or negative consequence that needs to be paid

references to the concept of cost or payment, particularly regarding societal implications

No Comments

No Known Activations