INDEX

Explanations

references to a specific location or country

oai_token-act-pair · gpt-3.5-turbo

references to the term "this" within various contexts

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

icons

-0.82

acers

-0.77

masters

-0.75

 Izan

-0.72

loads

-0.69

acer

-0.69

cks

-0.69

mates

-0.69

vich

-0.68

jac

-0.68

POSITIVE LOGITS

 particular

1.00

 regard

0.98

 week

0.95

 endeavor

0.92

 year

0.89

 hemisphere

0.87

 century

0.85

 endeavour

0.83

 country

0.83

 predicament

0.82

Activations Density 0.154%

references to a specific location or country

references to the term "this" within various contexts

No Comments

No Known Activations