INDEX

Explanations

the word "this."

oai_token-act-pair · gpt-3.5-turbo

references to specific moments or contexts in time

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

sylv

-0.65

keeper

-0.64

kens

-0.61

ratulations

-0.61

STEM

-0.60

scape

-0.59

ghan

-0.59

gre

-0.58

keepers

-0.58

ilies

-0.57

POSITIVE LOGITS

 behest

1.21

 expense

1.04

 outset

1.03

 intersections

0.96

 helm

0.93

 discretion

0.91

 insistence

0.87

 glance

0.86

 concess

0.82

 speeds

0.81

Activations Density 0.142%

the word "this."

references to specific moments or contexts in time

No Comments

No Known Activations