INDEX

Explanations

phrases or text indicating a new starting point or beginning

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the beginning of new events or actions

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

itsch

-0.83

thel

-0.71

cedented

-0.71

greg

-0.69

ingly

-0.69

ombat

-0.67

otropic

-0.66

atron

-0.65

ilit

-0.65

vertisement

-0.64

POSITIVE LOGITS

 anew

0.94

 salaries

0.75

XI

0.72

 point

0.68

 tomorrow

0.68

 TODAY

0.67

 ages

0.65

 Point

0.62

 pitcher

0.62

 inference

0.61

Activations Density 0.056%

phrases or text indicating a new starting point or beginning

phrases indicating the beginning of new events or actions

No Comments

No Known Activations