INDEX

Explanations

adjectives or phrases related to impactful or influential attributes

oai_token-act-pair · gpt-3.5-turbo

terms associated with emotional intensity and dramatic elements

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

 aborted

-0.68

 moratorium

-0.65

reports

-0.64

killed

-0.63

 repaired

-0.62

untary

-0.62

abbit

-0.60

 unprotected

-0.60

hooting

-0.59

ALK

-0.59

POSITIVE LOGITS

iness

1.02

lihood

0.99

enance

0.88

notations

0.84

tones

0.81

iveness

0.75

aic

0.74

vis

0.74

terness

0.72

uality

0.71

Activations Density 0.254%

adjectives or phrases related to impactful or influential attributes

terms associated with emotional intensity and dramatic elements

No Comments

No Known Activations