INDEX

Explanations

instances where someone is being specifically noted or mentioned in a text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "noted."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

heed

-0.74

ciating

-0.74

atan

-0.70

thood

-0.69

quer

-0.69

WAY

-0.66

ibur

-0.66

abase

-0.65

adesh

-0.65

icum

-0.63

POSITIVE LOGITS

unct

0.74

 inconsistencies

0.71

 noted

0.69

 deductions

0.68

 notes

0.68

 Schiff

0.66

 discrepancies

0.66

 prominently

0.66

 approving

0.66

Sta

0.64

Activations Density 0.027%

instances where someone is being specifically noted or mentioned in a text

instances of the word "noted."

No Comments

No Known Activations