INDEX

Explanations

verbs indicating action or behavior

oai_token-act-pair · gpt-3.5-turbo

action-oriented verbs and expressions related to engagement or involvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Applic

-0.79

LLP

-0.62

fts

-0.61

CLR

-0.61

pload

-0.61

amation

-0.60

wake

-0.59

 Applic

-0.59

 Organizations

-0.59

FTWARE

-0.58

POSITIVE LOGITS

backs

0.75

 ourselves

0.73

ings

0.67

idas

0.67

iencies

0.66

wright

0.66

fully

0.64

ida

0.63

ively

0.62

iens

0.61

Activations Density 0.377%

verbs indicating action or behavior

action-oriented verbs and expressions related to engagement or involvement

No Comments

No Known Activations