INDEX

Explanations

phrases indicating statements or declarations

oai_token-act-pair · gpt-3.5-turbo

references to assertions or statements made about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 guiActiveUnfocused

-0.68

rag

-0.66

 endif

-0.66

cheon

-0.63

icult

-0.61

activate

-0.59

cd

-0.59

othal

-0.59

agram

-0.58

nn

-0.58

POSITIVE LOGITS

 claims

3.55

 Claims

2.69

 claim

2.48

Claim

2.09

claim

2.07

 claimed

2.04

 allegations

2.01

 assertions

1.99

 Claim

1.90

 accusations

1.84

Activations Density 0.019%

phrases indicating statements or declarations

references to assertions or statements made about various subjects

No Comments

No Known Activations