INDEX

Explanations

phrases related to providing explanations or justifications

oai_token-act-pair · gpt-3.5-turbo

multiple instances of the word "reasons" indicating various justifications or causes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

yss

-0.68

 Winged

-0.68

 puck

-0.67

 franc

-0.66

 Pixie

-0.66

 needle

-0.64

ream

-0.63

 Mous

-0.63

enged

-0.62

esc

-0.62

POSITIVE LOGITS

why

0.91

 reasons

0.89

cale

0.84

WHY

0.84

pointers

0.83

 arguments

0.80

æĦ

0.78

 justifying

0.78

why

0.77

 explanations

0.75

Activations Density 0.020%

phrases related to providing explanations or justifications

multiple instances of the word "reasons" indicating various justifications or causes

No Comments

No Known Activations