INDEX

Explanations

mentions of television networks

oai_token-act-pair · gpt-3.5-turbo

references to a specific television network

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

flation

-0.66

val

-0.66

sql

-0.66

bats

-0.64

matter

-0.64

umatic

-0.64

BuyableInstoreAndOnline

-0.62

integer

-0.62

juries

-0.61

comes

-0.61

POSITIVE LOGITS

 networks

1.11

 network

1.10

 Networks

1.08

network

0.92

 affili

0.83

 connectivity

0.81

 Network

0.79

 Broadcast

0.78

 affiliates

0.77

 networking

0.75

Activations Density 0.018%

mentions of television networks

references to a specific television network

No Comments

No Known Activations