INDEX

Explanations

references to the television network ABC

oai_token-act-pair · gpt-3.5-turbo

mentions of the ABC network

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

vik

-0.76

oslav

-0.72

 reservation

-0.70

thood

-0.68

Mi

-0.64

 continental

-0.64

Footnote

-0.63

clave

-0.62

isl

-0.62

oit

-0.62

POSITIVE LOGITS

ABC

3.67

ABC

2.92

NBC

2.05

CBS

1.99

abc

1.70

PBS

1.69

FOX

1.67

CBC

1.66

ITV

1.56

NBC

1.54

Activations Density 0.012%

references to the television network ABC

mentions of the ABC network

No Comments

No Known Activations