INDEX

Explanations

the word "worse"

oai_token-act-pair · gpt-3.5-turbo

references to worsening situations or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ettes

-0.87

encers

-0.82

itialized

-0.79

ools

-0.77

ette

-0.75

etition

-0.75

heter

-0.73

oir

-0.72

ieu

-0.72

trl

-0.72

POSITIVE LOGITS

 than

1.12

 Than

1.05

 behaved

0.92

than

0.85

 nightmares

0.83

 catast

0.82

 nightmare

0.77

nces

0.75

 Ukrain

0.68

 undermin

0.68

Activations Density 0.020%

the word "worse"

references to worsening situations or conditions

No Comments

No Known Activations