INDEX

Explanations

information related to numerical values or statistics

oai_token-act-pair · gpt-3.5-turbo

phrases indicating numerical ranges or comparisons

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

ergic

-0.71

eless

-0.68

eval

-0.68

edia

-0.67

ires

-0.65

mitter

-0.64

pter

-0.63

ESE

-0.62

Ident

-0.62

ENE

-0.61

POSITIVE LOGITS

acle

1.25

chard

1.24

ifice

1.16

acles

1.12

ific

1.10

chid

1.09

lando

1.01

acular

1.00

nam

0.96

phans

0.91

Activations Density 0.069%

information related to numerical values or statistics

phrases indicating numerical ranges or comparisons

No Comments

No Known Activations