INDEX

Explanations

mentions of the country "Spain" or things related to Spanish culture

oai_token-act-pair · gpt-3.5-turbo

mentions of "Spanish" and "Spain"

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

ĸļ

-1.08

ertodd

-1.00

olulu

-0.96

mble

-0.95

oscope

-0.94

ochond

-0.84

ritic

-0.84

algia

-0.82

ostics

-0.80

gling

-0.80

POSITIVE LOGITS

 Inquisition

1.36

 Fork

0.86

 Nieto

0.84

 jails

0.79

 Libre

0.77

 Rican

0.76

 Rico

0.74

 unification

0.70

wings

0.70

pes

0.70

Activations Density 0.015%

mentions of the country "Spain" or things related to Spanish culture

mentions of "Spanish" and "Spain"

No Comments

No Known Activations