INDEX

Explanations

phrases indicating a minimum acceptable level or standard

oai_token-act-pair · gpt-3.5-turbo

expressions that minimize or downplay situations

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

clerosis

-0.77

kefeller

-0.72

axter

-0.69

 Berk

-0.67

 Codes

-0.65

 Travels

-0.64

 Lyndon

-0.63

 Blueprint

-0.62

iannopoulos

-0.61

thumbnails

-0.60

POSITIVE LOGITS

 conceivable

0.72

 recogn

0.69

 possible

0.69

 favourable

0.69

 plausible

0.66

 amount

0.65

uner

0.64

 imaginable

0.64

egu

0.64

 practicable

0.62

Activations Density 0.029%

phrases indicating a minimum acceptable level or standard

expressions that minimize or downplay situations

No Comments

No Known Activations