INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

the mention of specific gaming terms or references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

FORMATION

-0.80

fulness

-0.70

hower

-0.65

utral

-0.64

 fertility

-0.64

 Giov

-0.63

 spaced

-0.63

bury

-0.62

 cort

-0.62

 lane

-0.62

POSITIVE LOGITS

uably

1.54

uments

1.19

ansas

1.09

uable

0.98

raph

0.96

roup

0.94

emouth

0.92

entin

0.90

uin

0.88

eering

0.86

Activations Density 0.023%

proper nouns

the mention of specific gaming terms or references

No Comments

No Known Activations