INDEX

Explanations

words related to criticisms or descriptions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the prefix "di-" related to various contexts or 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

Negative Logits

witz

-0.75

 Rudd

-0.71

ï¸ı

-0.70

 totality

-0.69

INGS

-0.68

leigh

-0.67

ORTS

-0.66

ãģĨ

-0.64

 spare

-0.64

 Heard

-0.63

POSITIVE LOGITS

urnal

1.42

abol

1.39

ocese

1.36

abolic

1.25

agon

1.15

plom

1.12

ablo

1.11

agram

1.08

agonal

1.02

adem

1.02

Activations Density 0.018%

words related to criticisms or descriptions

occurrences of the prefix "di-" related to various contexts or subjects

No Known Activations