INDEX

Explanations

text related to recognition or acknowledgment

oai_token-act-pair · gpt-3.5-turbo

terms related to recognition and cognitive processes

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

 mileage

-0.71

bury

-0.69

scenes

-0.67

anwhile

-0.64

 setbacks

-0.64

HER

-0.63

CHAT

-0.63

hours

-0.62

RESULTS

-0.62

 Beir

-0.62

POSITIVE LOGITS

ition

1.11

isance

1.09

itives

1.06

ational

1.04

ocent

1.03

istic

1.01

unci

1.00

ormal

0.97

omore

0.95

ificent

0.95

Activations Density 0.012%

text related to recognition or acknowledgment

terms related to recognition and cognitive processes

No Comments

No Known Activations