INDEX

Explanations

scientific studies or research findings

oai_token-act-pair · gpt-3.5-turbo

the occurrence of the word "studies."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ward

-0.64

cycl

-0.60

IER

-0.59

nu

-0.57

 amino

-0.57

onz

-0.56

RAF

-0.56

cop

-0.56

âĹ¼

-0.55

 Lann

-0.55

POSITIVE LOGITS

uggest

1.08

udo

1.08

manship

0.89

ilk

0.84

hig

0.83

 studies

0.81

heet

0.80

study

0.79

hops

0.77

chool

0.77

Activations Density 0.026%

scientific studies or research findings

the occurrence of the word "studies."

No Comments

No Known Activations