INDEX

Explanations

names of people

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "P" 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 GOODMAN

-0.70

 underwater

-0.64

é¾įå¥ĳå£«

-0.62

 Rebels

-0.62

 vested

-0.62

 Definitive

-0.61

 compounded

-0.59

 extraction

-0.59

 bases

-0.58

 Thieves

-0.58

POSITIVE LOGITS

ivot

1.21

astern

1.19

rentice

1.17

urdy

1.15

oulos

1.13

onder

1.12

ohl

1.11

iment

1.10

itzer

1.09

onson

1.08

Activations Density 0.030%

names of people

occurrences of the letter "P" in various contexts

No Comments

No Known Activations