INDEX

Explanations

phrases related to storytelling and experiences of hardship

oai_token-act-pair · gpt-3.5-turbo

common conjunctions and prepositions indicating relationships between phrases or ideas

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

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

 Mate

-0.85

 Knot

-0.72

 Gong

-0.67

 Kham

-0.67

 Wake

-0.66

 Appeal

-0.66

Roe

-0.64

 Bundy

-0.63

 Balk

-0.62

 Buddy

-0.62

POSITIVE LOGITS

selves

0.96

terday

0.94

redients

0.92

mosp

0.92

theless

0.89

ilogy

0.88

etheless

0.85

yrinth

0.80

istar

0.79

umbai

0.77

Activations Density 0.226%

phrases related to storytelling and experiences of hardship

common conjunctions and prepositions indicating relationships between phrases or ideas

No Comments

No Known Activations