INDEX

Explanations

references to organized actions or initiatives with a specific goal

oai_token-act-pair · gpt-3.5-turbo

references to various types of campaigns

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

orgetown

-0.90

ĪĴ

-0.77

tics

-0.70

ews

-0.69

essional

-0.67

66666666

-0.66

essee

-0.64

ipt

-0.64

olen

-0.63

sembly

-0.63

POSITIVE LOGITS

 waged

0.90

 campaigns

0.90

 slogan

0.85

 manager

0.84

horse

0.83

 against

0.83

 trail

0.82

ulations

0.78

 undertaken

0.77

 slogans

0.75

Activations Density 0.035%

references to organized actions or initiatives with a specific goal

references to various types of campaigns

No Comments

No Known Activations