INDEX

Explanations

statements indicating action or decision-making

oai_token-act-pair · gpt-3.5-turbo

words and phrases indicating direct statements or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

tis

-0.77

currently

-0.76

enei

-0.74

alg

-0.70

wayne

-0.67

arel

-0.66

 ordinarily

-0.65

linked

-0.62

gae

-0.61

typically

-0.61

POSITIVE LOGITS

 wrong

0.77

 inappropriately

0.77

 Doct

0.71

 LAST

0.70

 mistakes

0.69

 beforehand

0.69

 last

0.69

 yesterday

0.67

ocument

0.65

ãĤ¤ãĥĪ

0.62

Activations Density 0.510%

statements indicating action or decision-making

words and phrases indicating direct statements or actions

No Comments

No Known Activations