INDEX

Explanations

reflexive pronouns and words related to deep immersion or engrossment in a subject or activity

oai_token-act-pair · gpt-3.5-turbo

words and phrases associated with immersive involvement in activities or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 favor

-0.67

 favour

-0.59

METHOD

-0.58

 direction

-0.57

recomm

-0.57

jab

-0.57

ovi

-0.57

BACK

-0.55

 Gemini

-0.55

ordan

-0.55

POSITIVE LOGITS

 therein

1.03

ined

0.75

edIn

0.70

gin

0.70

isse

0.69

in

0.68

deep

0.67

hani

0.65

ipel

0.64

ãĥĦ

0.64

Activations Density 0.214%

reflexive pronouns and words related to deep immersion or engrossment in a subject or activity

words and phrases associated with immersive involvement in activities or roles

No Comments

No Known Activations