INDEX

Explanations

words related to activities and events

oai_token-act-pair · gpt-3.5-turbo

nouns and terms related to events and activities

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

 withd

-0.68

 constitu

-0.63

 mete

-0.62

heastern

-0.59

 downstream

-0.58

 misguided

-0.56

irez

-0.56

 inadequate

-0.56

 ItemLevel

-0.55

successful

-0.54

POSITIVE LOGITS

pox

0.78

addle

0.74

0.70

iasis

0.70

isc

0.67

mask

0.66

WAR

0.64

coin

0.64

gate

0.63

wait

0.63

Activations Density 0.907%

words related to activities and events

nouns and terms related to events and activities

No Comments

No Known Activations