INDEX

Explanations

verbs that indicate action or activity

oai_token-act-pair · gpt-3.5-turbo

statements that describe the existence or presence of various concepts and elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

obook

-0.74

ocracy

-0.70

esis

-0.68

 unfocusedRange

-0.63

ipop

-0.63

aroo

-0.62

ographer

-0.62

phas

-0.62

phabet

-0.59

ropolis

-0.58

POSITIVE LOGITS

 respectively

1.56

 alike

1.26

 jointly

1.17

 mutually

1.13

 examples

1.02

 trademarks

1.00

 intertwined

0.99

 insepar

0.99

 fronts

0.96

 both

0.94

Activations Density 0.294%

verbs that indicate action or activity

statements that describe the existence or presence of various concepts and elements

No Comments

No Known Activations