INDEX

Explanations

words or partial words containing "res"

oai_token-act-pair · gpt-3.5-turbo

terms related to a specific location or venue

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

 Phar

-0.62

 Cruiser

-0.59

glers

-0.59

 Hawaiian

-0.58

 kilomet

-0.57

 Hein

-0.56

 Pebble

-0.56

 snippets

-0.56

âĢ¢âĢ¢

-0.56

 Camel

-0.56

POSITIVE LOGITS

istance

1.38

idency

1.30

olutions

1.14

cue

1.14

idence

1.07

urrection

1.06

pring

1.04

olver

1.00

idents

0.99

istor

0.98

Activations Density 0.011%

words or partial words containing "res"

terms related to a specific location or venue

No Comments

No Known Activations