INDEX

Explanations

rhetorical questions

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

questions, particularly those related to mysteries or unknown information

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ikuman

-0.80

arm

-0.77

eared

-0.69

cipled

-0.68

 practition

-0.67

armed

-0.65

elist

-0.65

rio

-0.63

peg

-0.63

legged

-0.62

POSITIVE LOGITS

 Answer

1.42

Answer

1.26

 Wouldn

1.22

 Surely

1.21

 Does

1.13

 Certainly

1.11

 Would

1.10

Why

1.09

 Answers

1.09

 Could

1.08

Activations Density 0.113%

rhetorical questions

questions, particularly those related to mysteries or unknown information

No Comments

No Known Activations