INDEX

Explanations

names or initials starting with the letter "M" followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

the letter 'M' 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 evid

-0.68

nav

-0.61

 following

-0.60

 hots

-0.59

 Beyond

-0.59

 coupled

-0.59

 derivative

-0.59

 Breaking

-0.59

 cause

-0.58

 apart

-0.58

POSITIVE LOGITS

oller

1.17

eeks

1.15

atson

1.11

aimon

1.10

igrant

1.08

laden

1.08

erton

1.08

oust

1.07

aunder

1.07

antle

1.07

Activations Density 0.028%

names or initials starting with the letter "M" followed by a numerical value

the letter 'M' in various contexts

No Comments

No Known Activations