INDEX

Explanations

terms related to transformation or conversion

oai_token-act-pair · gpt-3.5-turbo

the preposition "into" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 challeng

-0.71

 Seym

-0.67

 ironically

-0.65

 rightfully

-0.64

entimes

-0.64

 Niet

-0.64

 conduc

-0.63

 intimid

-0.63

 conveyed

-0.62

 Barron

-0.60

POSITIVE LOGITS

 infinity

0.76

 adulthood

0.75

 Eternity

0.72

 orbit

0.71

tha

0.69

vernment

0.67

clusions

0.66

iotic

0.65

 Darkness

0.65

 existence

0.63

Activations Density 0.031%

terms related to transformation or conversion

the preposition "into" in various contexts

No Comments

No Known Activations