INDEX

Explanations

words related to perception, especially phrases related to how things are perceived

oai_token-act-pair · gpt-3.5-turbo

terms related to perception and its implications or interpretations

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

estones

-0.75

sit

-0.72

eni

-0.72

Interstitial

-0.71

swick

-0.68

contract

-0.68

gre

-0.67

ceed

-0.66

hatt

-0.65

loads

-0.65

POSITIVE LOGITS

 perceptions

0.87

 Perception

0.86

 perception

0.86

 impressions

0.76

 impression

0.74

ally

0.74

Wiz

0.72

terness

0.70

 opin

0.69

 Illusion

0.68

Activations Density 0.025%

words related to perception, especially phrases related to how things are perceived

terms related to perception and its implications or interpretations

No Comments

No Known Activations