INDEX

Explanations

words related to locations or areas that are considered significant or important

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of "hots" and "Hots," which seem to refer to hotspot-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

xit

-0.77

ftime

-0.72

Reviewer

-0.71

ogy

-0.68

utral

-0.65

naissance

-0.65

 miscarriage

-0.64

yss

-0.64

 syll

-0.63

^^^^

-0.63

POSITIVE LOGITS

pots

1.30

pot

1.19

combe

1.04

 Hots

1.02

 hots

0.93

peak

0.86

atile

0.81

pur

0.81

bour

0.79

apped

0.77

Activations Density 0.014%

words related to locations or areas that are considered significant or important

repeated mentions of "hots" and "Hots," which seem to refer to hotspot-related contexts

No Comments

No Known Activations