INDEX

Explanations

references to a specific television network

oai_token-act-pair · gpt-3.5-turbo

mentions of the FOX 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ucket

-0.79

adding

-0.70

agn

-0.68

anks

-0.68

haps

-0.68

ivari

-0.67

antics

-0.67

idences

-0.67

alli

-0.66

accompanied

-0.66

POSITIVE LOGITS

FOX

1.19

conn

0.98

çīĪ

0.86

FOX

0.82

fox

0.77

DEV

0.76

 Fest

0.76

NEWS

0.74

TAG

0.73

CAST

0.70

Activations Density 0.004%

references to a specific television network

mentions of the FOX network

No Comments

No Known Activations