INDEX

Explanations

sports team names and match schedules

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to sports teams and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

cffff

-0.84

tml

-0.77

soType

-0.69

ngth

-0.69

nown

-0.67

 decoration

-0.66

zsche

-0.66

inventoryQuantity

-0.66

olulu

-0.65

 euphem

-0.65

POSITIVE LOGITS

vs

1.75

 versus

1.37

vs

1.24

Vs

1.23

 wins

1.14

 defeated

1.10

VS

1.09

 defeats

1.04

 beating

1.00

Winner

0.99

Activations Density 0.203%

sports team names and match schedules

proper nouns related to sports teams and events

No Comments

No Known Activations