INDEX

Explanations

text indicating whether something is legitimate or in compliance with regulations

oai_token-act-pair · gpt-3.5-turbo

terms related to validity or being valid 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hedon

-0.79

Mania

-0.62

mania

-0.62

 superflu

-0.60

Kut

-0.60

seek

-0.60

hedral

-0.59

xual

-0.59

warts

-0.58

 traged

-0.58

POSITIVE LOGITS

ating

1.41

ators

1.38

ator

1.30

ates

1.10

ated

1.08

ations

1.07

ation

0.98

atable

0.90

ATING

0.90

alties

0.90

Activations Density 0.057%

text indicating whether something is legitimate or in compliance with regulations

terms related to validity or being valid in various contexts

No Comments

No Known Activations