INDEX

Explanations

phrases introducing speculation or possibilities

oai_token-act-pair · gpt-3.5-turbo

the word "perhaps," indicating uncertainty or speculation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

akes

-0.80

cium

-0.79

endar

-0.76

eral

-0.75

iphate

-0.74

say

-0.73

eph

-0.72

gem

-0.72

ature

-0.72

ship

-0.71

POSITIVE LOGITS

 unsurprisingly

1.47

 sensing

1.04

 unsur

1.03

 surprisingly

1.02

 reflecting

0.96

 predictably

0.93

 ironically

0.92

 understandably

0.89

 unwittingly

0.87

 embold

0.86

Activations Density 0.049%

phrases introducing speculation or possibilities

the word "perhaps," indicating uncertainty or speculation

No Comments

No Known Activations