INDEX

Explanations

numerical values in a structured format, particularly those related to measurements

oai_token-act-pair · gpt-3.5-turbo

numerical values and metrics related to data and statistics

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

 bureaucr

-0.60

 conce

-0.59

Recomm

-0.53

 objection

-0.53

 Salvation

-0.51

SCH

-0.50

 Sher

-0.50

compan

-0.49

 corpor

-0.48

SOC

-0.48

POSITIVE LOGITS

milo

0.81

adeon

0.74

rican

0.65

pring

0.64

braska

0.64

umenthal

0.64

anye

0.63

anwhile

0.62

ifice

0.62

ulic

0.61

Activations Density 0.440%

numerical values in a structured format, particularly those related to measurements

numerical values and metrics related to data and statistics

No Comments

No Known Activations