INDEX

Explanations

the concept or idea being discussed or mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

references to concepts or ideas labeled as "notions."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

avez

-0.63

Es

-0.61

annis

-0.60

gio

-0.57

acca

-0.57

pez

-0.56

 conserv

-0.55

adra

-0.55

aqu

-0.55

opal

-0.55

POSITIVE LOGITS

ually

1.09

ally

1.05

rack

0.98

naire

0.92

ality

0.92

ively

0.90

edly

0.86

eers

0.86

notations

0.78

lessly

0.78

Activations Density 0.031%

the concept or idea being discussed or mentioned in the text

references to concepts or ideas labeled as "notions."

No Comments

No Known Activations