INDEX

Explanations

names of countries in South America, with a particularly high focus on Colombia

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Colombia" and phrases related to it

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

lopp

-0.84

oppable

-0.81

jri

-0.80

wered

-0.79

umbnails

-0.75

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.74

eter

-0.74

mith

-0.73

ership

-0.73

ancies

-0.72

POSITIVE LOGITS

 Colombia

0.98

 Peru

0.91

 Uruguay

0.79

 Colomb

0.79

 Beans

0.77

 Congo

0.77

 Colombian

0.75

pes

0.74

vernment

0.74

 beans

0.72

Activations Density 0.007%

names of countries in South America, with a particularly high focus on Colombia

occurrences of the word "Colombia" and phrases related to it

No Comments

No Known Activations