INDEX

Explanations

occurrences of the word "to"

oai_token-act-pair · gpt-3.5-turbo

the phrase "seems to" used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

called

-0.68

ashes

-0.67

noticed

-0.62

imore

-0.61

finding

-0.61

opens

-0.61

endale

-0.60

items

-0.60

types

-0.60

ãĤ¦ãĤ¹

-0.59

POSITIVE LOGITS

 imply

1.13

 contradict

1.09

 defy

1.07

 indicate

1.03

 condone

1.03

be

0.99

me

0.99

 embody

0.97

 confirm

0.92

 correlate

0.92

Activations Density 0.054%

occurrences of the word "to"

the phrase "seems to" used in various contexts

No Comments

No Known Activations