INDEX

Explanations

the word "Perhaps" at the beginning of sentences

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Perhaps"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

emy

-0.85

rieg

-0.78

zeb

-0.77

efer

-0.75

ioch

-0.75

sbm

-0.74

vance

-0.72

nen

-0.71

chens

-0.71

lined

-0.71

POSITIVE LOGITS

 someday

0.89

 unsurprisingly

0.87

 sensing

0.80

haps

0.76

 Admir

0.74

 tempted

0.73

 embold

0.71

 opio

0.67

 involuntary

0.64

 unsur

0.63

Activations Density 0.026%

the word "Perhaps" at the beginning of sentences

instances of the word "Perhaps"

No Comments

No Known Activations