INDEX

Explanations

phrases related to statements or declarations of varying levels of certainty

oai_token-act-pair · gpt-3.5-turbo

non-standard or unconventional characters or symbols in text

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

 Dirt

-0.77

 deprivation

-0.71

 scattering

-0.70

 dumping

-0.68

 guiActiveUnfocused

-0.68

 Palest

-0.67

 steroids

-0.67

 personality

-0.67

 charisma

-0.66

gib

-0.66

POSITIVE LOGITS

£

0.96

agree

0.93

¹

0.92

should

0.92

Ì

0.91

º

0.91

have

0.84

â

0.84

must

0.83

¬

0.81

Activations Density 0.175%

phrases related to statements or declarations of varying levels of certainty

non-standard or unconventional characters or symbols in text

No Comments

No Known Activations