INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

the word "so" 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 @ 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

DERR

-0.66

 trespass

-0.62

 deficit

-0.62

 races

-0.61

 appra

-0.60

 prose

-0.60

 curves

-0.60

 separ

-0.59

 shutter

-0.58

 disbelief

-0.57

POSITIVE LOGITS

fter

1.09

aked

1.06

oner

1.05

FTWARE

1.04

bered

1.04

ppy

1.00

ooo

0.99

oooo

0.98

zzo

0.95

oths

0.95

Activations Density 0.039%

proper nouns

the word "so" in various contexts

No Comments

No Known Activations