INDEX

Explanations

phrases related to uncertainty or comparison

oai_token-act-pair · gpt-3.5-turbo

references to uncertainty or speculation

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

çīĪ

-0.71

seys

-0.64

hester

-0.64

DOM

-0.62

 paternity

-0.62

 immunity

-0.61

 VIDEOS

-0.61

awaru

-0.60

 coefficients

-0.59

mares

-0.58

POSITIVE LOGITS

arily

0.80

umbn

0.71

adj

0.71

 integral

0.70

filled

0.68

 happiest

0.67

lier

0.66

lled

0.66

alysed

0.66

opped

0.65

Activations Density 0.287%

phrases related to uncertainty or comparison

references to uncertainty or speculation

No Comments

No Known Activations