INDEX

Explanations

phrases indicating successful outcomes or achievements

oai_token-act-pair · gpt-3.5-turbo

instances of the word "successfully"

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Ancients

-0.68

 Warcraft

-0.68

 Rober

-0.66

 newsletters

-0.65

 Relief

-0.64

 Origin

-0.63

Orig

-0.61

Eth

-0.61

 Flames

-0.61

 anonymity

-0.59

POSITIVE LOGITS

 succeed

0.89

 reproduce

0.88

 successfully

0.85

 destro

0.83

 navig

0.82

 achieved

0.81

 competed

0.78

 mastered

0.77

 exting

0.76

TAIN

0.76

Activations Density 0.005%

phrases indicating successful outcomes or achievements

instances of the word "successfully"

No Known Activations