INDEX

Explanations

phrases emphasizing a specific idea or point

oai_token-act-pair · gpt-3.5-turbo

references to important messages or themes

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

engeance

-0.73

ords

-0.71

urses

-0.68

erenn

-0.68

ENCY

-0.67

agonists

-0.67

enses

-0.65

itates

-0.65

umbers

-0.65

endars

-0.64

POSITIVE LOGITS

 message

1.05

 messages

1.00

 Messages

0.91

message

0.91

 conveyed

0.87

board

0.83

posts

0.83

FontSize

0.82

 goodbye

0.80

Message

0.77

Activations Density 0.025%

phrases emphasizing a specific idea or point

references to important messages or themes

No Comments

No Known Activations