INDEX

Explanations

references to the word "somewhat"

oai_token-act-pair · gpt-3.5-turbo

variations of the word "somewhat" and related terms, indicating uncertainty or vagueness

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

ãĥ¼ãĥĨ

-0.76

 Carnage

-0.74

eering

-0.71

FU

-0.66

arium

-0.65

ALLY

-0.64

ELS

-0.63

senal

-0.63

nor

-0.62

alities

-0.62

POSITIVE LOGITS

terday

0.96

orld

0.75

hig

0.74

ramid

0.73

ource

0.72

ague

0.72

stairs

0.71

chedel

0.70

 whisper

0.68

heed

0.67

Activations Density 0.044%

references to the word "somewhat"

variations of the word "somewhat" and related terms, indicating uncertainty or vagueness

No Comments

No Known Activations