INDEX

Explanations

plural nouns

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

words related to possessives or ownership

oai_token-act-pair · gpt-3.5-turbo

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

 Reef

-0.72

milo

-0.62

 stacks

-0.61

 slab

-0.60

Bey

-0.60

EStream

-0.59

 Dell

-0.59

 lapt

-0.58

å¿

-0.58

ãĥ¼ãĥĨ

-0.58

POSITIVE LOGITS

ources

0.98

alty

0.89

lightly

0.88

uez

0.87

aved

0.82

agara

0.79

ELF

0.79

ushi

0.79

essions

0.79

ideshow

0.77

Activations Density 0.116%

plural nouns

words related to possessives or ownership

No Comments

No Known Activations