INDEX

Explanations

words related to negative outcomes or worsening situations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a decline or worsening situation

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

ĳå£«

-0.73

ools

-0.71

cot

-0.65

cock

-0.65

romy

-0.61

poke

-0.61

OPLE

-0.59

esp

-0.59

itle

-0.58

ouch

-0.58

POSITIVE LOGITS

 exponentially

0.84

 progressively

0.81

 veter

0.73

 steadily

0.71

 each

0.70

 gradually

0.69

 than

0.69

 yearly

0.68

 every

0.65

Winged

0.65

Activations Density 0.127%

words related to negative outcomes or worsening situations

phrases indicating a decline or worsening situation

No Comments

No Known Activations