INDEX

Explanations

events or actions in a specified time frame

oai_token-act-pair · gpt-3.5-turbo

key action verbs related to events and their occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

itu

-0.66

Advertisements

-0.63

heid

-0.62

wy

-0.61

aq

-0.60

usercontent

-0.60

truth

-0.60

quit

-0.60

yes

-0.59

opathic

-0.57

POSITIVE LOGITS

 prompted

0.80

undown

0.76

romeda

0.74

 housed

0.72

 dubbed

0.71

 culmin

0.71

 Beir

0.71

 Bates

0.68

ktop

0.66

 spurred

0.65

Activations Density 0.495%

events or actions in a specified time frame

key action verbs related to events and their occurrences

No Comments

No Known Activations