INDEX

Explanations

modifications or variations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "modified" and related variations

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

çĦ

-0.83

True

-0.69

OPA

-0.69

Ranked

-0.68

mp

-0.67

velt

-0.66

doms

-0.66

vor

-0.65

FORE

-0.65

Rect

-0.64

POSITIVE LOGITS

atile

0.95

hap

0.83

iations

0.81

 versions

0.77

 wrench

0.77

atility

0.76

ively

0.76

 organisms

0.75

itized

0.75

 racks

0.73

Activations Density 0.020%

modifications or variations

instances of the word "modified" and related variations

No Comments

No Known Activations