INDEX

Explanations

references to specific people and names in the text

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

proper nouns, possibly related to names, locations, or organizations

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 sqor

-0.74

Cla

-0.74

mental

-0.74

CHAR

-0.70

Hung

-0.69

sal

-0.67

 meters

-0.66

 Miranda

-0.65

POSITIVE LOGITS

ocy

1.13

oad

1.12

ow

1.11

Ã³

1.08

os

1.08

Åį

1.06

ou

1.06

opa

1.05

1.04

ov

1.04

Activations Density 0.216%

references to specific people and names in the text

proper nouns, possibly related to names, locations, or organizations

No Comments

No Known Activations