INDEX

Explanations

conjunctions, particularly the word "or"

oai_token-act-pair · gpt-3.5-turbo

the word "or" in various contexts indicating alternatives or options

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 horizont

-0.60

onday

-0.60

"}],"

-0.57

ocracy

-0.57

 vulner

-0.57

eryl

-0.56

 Malone

-0.55

Byr

-0.55

 Holmes

-0.55

Dear

-0.54

POSITIVE LOGITS

chard

1.31

Else

1.25

acle

1.14

lando

1.13

acles

1.09

acular

1.07

chid

1.03

 else

0.98

phan

0.97

nery

0.97

Activations Density 0.036%

conjunctions, particularly the word "or"

the word "or" in various contexts indicating alternatives or options

No Comments

No Known Activations