INDEX

Explanations

mentions of specific terms or topics within a larger context

oai_token-act-pair · gpt-3.5-turbo

instances of the word "mention" and related phrases regarding acknowledgment or referencing something

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

 Fulton

-0.71

ICLE

-0.69

 nerv

-0.67

adobe

-0.66

 hijacked

-0.66

 McCorm

-0.63

 hottest

-0.63

 contracting

-0.62

 Stam

-0.60

Cod

-0.60

POSITIVE LOGITS

eful

0.82

aterasu

0.77

 whatsoever

0.75

blance

0.75

phasis

0.74

ible

0.71

catentry

0.70

 emphasis

0.69

smanship

0.69

backs

0.69

Activations Density 0.223%

mentions of specific terms or topics within a larger context

instances of the word "mention" and related phrases regarding acknowledgment or referencing something

No Comments

No Known Activations