INDEX

Explanations

phrases related to events or situations that are happening or unfolding

oai_token-act-pair · gpt-3.5-turbo

phrases questioning or discussing uncertainty or confusion about ongoing events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gart

-0.76

 Desk

-0.59

vale

-0.57

 helper

-0.56

ilts

-0.52

aspers

-0.52

stra

-0.52

aser

-0.52

oola

-0.51

 Fiat

-0.50

POSITIVE LOGITS

 wrong

0.91

on

0.79

 nuts

0.75

 happening

0.71

 viral

0.69

 happen

0.66

aw

0.66

 forth

0.65

 dstg

0.65

wrong

0.65

Activations Density 0.027%

phrases related to events or situations that are happening or unfolding

phrases questioning or discussing uncertainty or confusion about ongoing events

No Comments

No Known Activations