INDEX

Explanations

phrases indicating permission or possibility

oai_token-act-pair · gpt-3.5-turbo

instances of the word "may" indicating possibility or permission

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

ging

-0.88

 Fighter

-0.74

hran

-0.70

ocracy

-0.70

ged

-0.68

cheon

-0.66

 Composite

-0.66

ãĥ¼ãĥ«

-0.64

masters

-0.63

 Dirty

-0.63

POSITIVE LOGITS

hap

0.98

haps

0.96

onna

0.92

 optionally

0.91

be

0.87

entimes

0.87

 confuse

0.82

 derive

0.80

 alternatively

0.80

adian

0.79

Activations Density 0.070%

phrases indicating permission or possibility

instances of the word "may" indicating possibility or permission

No Comments

No Known Activations