INDEX

Explanations

verbs or phrases related to implying or suggesting something

oai_token-act-pair · gpt-3.5-turbo

words related to implications or causation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

SEA

-0.74

Ĥ¬

-0.72

zanne

-0.69

grass

-0.68

Lago

-0.67

lda

-0.65

qua

-0.64

thin

-0.63

ĪĴ

-0.63

Ward

-0.63

POSITIVE LOGITS

oded

1.21

anting

1.13

osion

1.13

icate

1.11

icating

1.10

icates

1.09

ausible

1.07

 impl

1.07

oding

1.04

anted

0.99

Activations Density 0.007%

verbs or phrases related to implying or suggesting something

words related to implications or causation

No Comments

No Known Activations