INDEX

Explanations

phrases related to legal or regulatory contexts

oai_token-act-pair · gpt-3.5-turbo

the article "an" 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 @ 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

BLE

-0.81

 scares

-0.71

 pupils

-0.70

hood

-0.69

 spreads

-0.69

Things

-0.68

 psychiat

-0.66

bots

-0.66

Wid

-0.64

cules

-0.64

POSITIVE LOGITS

abolic

1.08

onym

1.03

agram

1.02

esthetic

0.93

cients

0.92

alogue

0.91

unciation

0.89

omal

0.88

onymous

0.88

ormal

0.87

Activations Density 0.268%

phrases related to legal or regulatory contexts

the article "an" in various contexts

No Comments

No Known Activations