INDEX

Explanations

words related to possibilities or potential outcomes

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "might."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

oric

-0.77

cies

-0.76

rett

-0.71

ament

-0.68

 Lauder

-0.67

 Constant

-0.66

ials

-0.66

pires

-0.65

shall

-0.64

inates

-0.63

POSITIVE LOGITS

 someday

1.06

 conce

0.97

 feas

0.91

ily

0.88

be

0.88

haps

0.84

iest

0.83

aea

0.83

 mistakenly

0.81

 offend

0.81

Activations Density 0.039%

words related to possibilities or potential outcomes

occurrences of the word "might."

No Comments

No Known Activations