INDEX

Explanations

instances of the word "to."

oai_token-act-pair · gpt-3.5-turbo

expressions of satisfaction or fulfillment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

olor

-0.75

imaru

-0.66

shield

-0.64

ipedia

-0.63

 Slash

-0.62

 Yard

-0.62

(%)

-0.61

ãĥ£

-0.60

iken

-0.59

 dummy

-0.59

POSITIVE LOGITS

 festive

0.68

 Apex

0.66

appropriately

0.64

Ep

0.64

abc

0.63

Ability

0.63

putable

0.63

 Beauty

0.62

 dign

0.62

 Ragnarok

0.62

Activations Density 0.000%

instances of the word "to."

expressions of satisfaction or fulfillment

No Comments

No Known Activations