INDEX

Explanations

names starting with "Gav"

oai_token-act-pair · gpt-3.5-turbo

references to individuals with the name "Gav" or variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

backer

-0.72

©¶æ

-0.66

 trademark

-0.66

utenant

-0.62

 Turing

-0.62

 profiling

-0.61

 phenomen

-0.61

LOAD

-0.61

 entitlement

-0.60

POS

-0.59

POSITIVE LOGITS

irus

1.27

oided

1.13

ascular

1.12

ille

1.11

arro

1.09

atars

1.08

ision

1.03

iral

1.01

enture

1.01

oice

1.00

Activations Density 0.020%

names starting with "Gav"

references to individuals with the name "Gav" or variations of it

No Comments

No Known Activations