INDEX

Explanations

phrases indicating recommendations or suggestions

oai_token-act-pair · gpt-3.5-turbo

statements expressing obligations or recommendations

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

Not in Any Lists

No Comments

Negative Logits

reality

-0.70

 Puzzle

-0.69

locked

-0.67

atile

-0.67

 Trails

-0.65

ITED

-0.61

Soul

-0.61

ãĥŃ

-0.59

 Vers

-0.58

cule

-0.58

POSITIVE LOGITS

be

0.94

ered

0.92

 ideally

0.85

 preferably

0.82

ering

0.81

 rightfully

0.80

 surely

0.78

 definitely

0.78

othal

0.77

 probably

0.76

Activations Density 0.059%

phrases indicating recommendations or suggestions

statements expressing obligations or recommendations

No Comments

No Known Activations