INDEX

Explanations

interviews or conversations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating interviews or discussions with specific subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 ILCS

-0.89

battle

-0.76

acci

-0.70

gra

-0.70

 thereof

-0.68

years

-0.67

.''.

-0.66

 separ

-0.65

fuck

-0.65

fights

-0.64

POSITIVE LOGITS

 reporters

0.98

 Oprah

0.94

 filmmaker

0.94

 Vanity

0.93

 Rolling

0.90

 Conan

0.90

 CNBC

0.89

 journalist

0.89

 Wired

0.88

 interviewer

0.88

Activations Density 0.074%

interviews or conversations

phrases indicating interviews or discussions with specific subjects

No Comments

No Known Activations