INDEX

Explanations

mentions of the acronym "BO" with associated numbers indicating some kind of scale or ranking

oai_token-act-pair · gpt-3.5-turbo

occurrences of "BO" and "LO" which are likely abbreviations or codes in a context involving sports or health statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

imental

-0.80

gew

-0.80

mary

-0.79

ional

-0.79

ources

-0.78

geist

-0.76

iment

-0.74

alez

-0.72

icago

-0.71

alia

-0.68

POSITIVE LOGITS

BO

1.04

OTH

0.93

OM

0.92

ARD

0.91

OSE

0.87

OTS

0.87

PET

0.86

bably

0.86

ARDS

0.86

leans

0.85

Activations Density 0.007%

mentions of the acronym "BO" with associated numbers indicating some kind of scale or ranking

occurrences of "BO" and "LO" which are likely abbreviations or codes in a context involving sports or health statistics

No Comments

No Known Activations