INDEX

Explanations

phrases related to decision-making or providing instructions

oai_token-act-pair · gpt-3.5-turbo

phrases related to accountability and decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 died

-0.83

 hanged

-0.72

 blasted

-0.72

 vanished

-0.71

 eighty

-0.70

 stunned

-0.70

 Negro

-0.70

 Yankee

-0.69

kefeller

-0.69

 revol

-0.69

POSITIVE LOGITS

 Ideally

1.39

 Examples

1.25

 Provide

1.24

Examples

1.24

Specific

1.19

 Lastly

1.19

optional

1.14

Lastly

1.13

 Ensure

1.13

 Include

1.12

Activations Density 0.389%

phrases related to decision-making or providing instructions

phrases related to accountability and decision-making processes

No Comments

No Known Activations