INDEX

Explanations

references to a specific location, specifically "Antalya"

oai_token-act-pair · gpt-3.5-turbo

words that are related to locations or geographical references

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

aciously

-0.85

ENTION

-0.78

éŃĶ

-0.76

ensable

-0.69

Legend

-0.64

sequence

-0.64

ancial

-0.64

rosse

-0.63

Oak

-0.63

Perfect

-0.63

POSITIVE LOGITS

tics

1.19

sts

1.03

zing

0.96

pse

0.92

zed

0.92

zer

0.89

tic

0.87

zers

0.84

gdala

0.84

vati

0.79

Activations Density 0.016%

references to a specific location, specifically "Antalya"

words that are related to locations or geographical references

No Comments

No Known Activations