INDEX

Explanations

phrases or words related to a specific name or topic

oai_token-act-pair · gpt-3.5-turbo

references to the term "Ho" alongside associated numerical values or identifiers

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 totality

-0.74

ications

-0.70

omething

-0.68

ãĤ¼ãĤ¦ãĤ¹

-0.66

 confir

-0.65

icate

-0.65

 Commonwealth

-0.64

CPC

-0.64

ication

-0.64

 mileage

-0.64

POSITIVE LOGITS

ppy

1.19

pper

1.14

arding

1.11

pping

1.07

gey

1.07

oney

1.05

LLOW

1.04

xton

1.00

ppe

0.99

eful

0.98

Activations Density 0.016%

phrases or words related to a specific name or topic

references to the term "Ho" alongside associated numerical values or identifiers

No Comments

No Known Activations