INDEX

Explanations

strings of characters typically related to coding and programming

oai_token-act-pair · gpt-3.5-turbo

words that refer to articles or content related to "ars" or "arsenic."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

states

-0.69

 slips

-0.66

 Pearce

-0.65

 coli

-0.61

lectic

-0.60

 STATES

-0.59

 revert

-0.59

FAULT

-0.59

 oxid

-0.59

 Biden

-0.58

POSITIVE LOGITS

hip

1.18

hips

1.14

hod

1.05

mith

1.04

ystem

1.01

cale

0.99

DragonMagazine

0.98

ansas

0.98

omething

0.93

itect

0.90

Activations Density 0.022%

strings of characters typically related to coding and programming

words that refer to articles or content related to "ars" or "arsenic."

No Comments

No Known Activations