INDEX

Explanations

detailed descriptions or narrations provided by eyewitnesses

oai_token-act-pair · gpt-3.5-turbo

references to different types of accounts and eyewitness testimonies

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

enta

-0.84

bledon

-0.84

OPA

-0.82

lahoma

-0.71

oku

-0.71

olicy

-0.70

ertodd

-0.69

pex

-0.69

upid

-0.68

Python

-0.65

POSITIVE LOGITS

 narr

1.11

ewitness

1.08

 tales

1.06

 narrated

1.05

 recounted

1.03

 corrobor

1.03

 narration

1.02

 testimonies

0.97

 relayed

0.95

 anecdotes

0.95

Activations Density 0.176%

detailed descriptions or narrations provided by eyewitnesses

references to different types of accounts and eyewitness testimonies

No Comments

No Known Activations