INDEX

Explanations

phrases related to test reviews or feedback

oai_token-act-pair · gpt-3.5-turbo

negative or critical sentiments in the context of reviews or evaluations

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

FML

-0.66

 Floyd

-0.64

 Conflict

-0.63

 Entered

-0.61

 âĢº

-0.60

 Compton

-0.60

 chirop

-0.59

 Smash

-0.58

MT

-0.58

 ranc

-0.57

POSITIVE LOGITS

related

0.85

element

0.85

arching

0.84

users

0.83

something

0.83

sweet

0.82

example

0.81

è¦ļéĨĴ

0.81

bearing

0.79

themed

0.79

Activations Density 0.350%

phrases related to test reviews or feedback

negative or critical sentiments in the context of reviews or evaluations

No Comments

No Known Activations