INDEX

Explanations

phrases indicating uncertainty or incompleteness

oai_token-act-pair · gpt-3.5-turbo

phrases indicating uncertainty or lack of completeness

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

 Emin

-0.76

 Seat

-0.67

 TAMADRA

-0.65

 Gore

-0.63

limit

-0.63

oru

-0.62

Dat

-0.62

 subsequ

-0.61

 Supervisor

-0.60

Pages

-0.60

POSITIVE LOGITS

 anymore

0.89

nor

0.87

 appe

0.79

 effected

0.70

 bothered

0.68

necess

0.66

 necessarily

0.66

yet

0.64

achable

0.64

TPPStreamerBot

0.64

Activations Density 0.070%

phrases indicating uncertainty or incompleteness

phrases indicating uncertainty or lack of completeness

No Comments

No Known Activations