INDEX

Explanations

the word "lots" followed by other words or phrases

oai_token-act-pair · gpt-3.5-turbo

the occurrence of the word "lots."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

roit

-0.58

 outpost

-0.57

 ethos

-0.55

 Correspond

-0.54

ensis

-0.54

 Advocate

-0.53

 masterpiece

-0.51

 Buddhism

-0.51

 Sinn

-0.51

 maxim

-0.50

POSITIVE LOGITS

of

0.93

entimes

0.87

poons

0.87

 thereof

0.82

ourcing

0.82

illions

0.80

luster

0.77

pread

0.75

pots

0.75

ãĤ§

0.75

Activations Density 0.038%

the word "lots" followed by other words or phrases

the occurrence of the word "lots."

No Comments

No Known Activations