INDEX

Explanations

names involving "Shi" or terms related to radiology

oai_token-act-pair · gpt-3.5-turbo

mention of specific individuals or characters

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

rants

-0.94

rant

-0.88

CENT

-0.83

fulness

-0.82

bender

-0.75

FactoryReloaded

-0.75

fully

-0.73

rish

-0.73

laus

-0.72

ungle

-0.72

POSITIVE LOGITS

arily

0.75

 Dull

0.71

hiba

0.70

velength

0.69

istics

0.67

arity

0.66

omics

0.64

opsis

0.64

ary

0.64

andum

0.64

Activations Density 0.046%

names involving "Shi" or terms related to radiology

mention of specific individuals or characters

No Comments

No Known Activations