INDEX

Explanations

locations where individuals are taken or transported to

oai_token-act-pair · gpt-3.5-turbo

instances of the word "where."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 striking

-0.72

ets

-0.69

 nutshell

-0.61

ÂłÂłÂłÂłÂłÂłÂłÂł

-0.61

 pace

-0.58

 chronological

-0.57

cycle

-0.56

et

-0.55

 squeeze

-0.54

 variability

-0.54

POSITIVE LOGITS

upon

1.44

abouts

0.91

fore

0.86

soever

0.81

abama

0.79

Īè

0.76

[|

0.72

arton

0.70

ngth

0.69

artment

0.69

Activations Density 0.054%

locations where individuals are taken or transported to

instances of the word "where."

No Comments

No Known Activations