INDEX

Explanations

food items and locations

oai_token-act-pair · gpt-3.5-turbo

lists or categorizations of items and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 exha

-0.67

 misunder

-0.65

interstitial

-0.65

Reward

-0.65

¬¼

-0.61

:(

-0.59

 enthusi

-0.58

iple

-0.58

quist

-0.57

bishop

-0.57

POSITIVE LOGITS

huh

1.11

etc

1.04

 albeit

1.01

 alas

0.97

eh

0.91

 however

0.91

 preferably

0.89

 meanwhile

0.88

 though

0.84

yes

0.82

Activations Density 0.754%

food items and locations

lists or categorizations of items and activities

No Comments

No Known Activations