INDEX

Explanations

years or dates mentioned as part of historical events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" and its associated temporal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

complex

-0.81

 texted

-0.74

-->

-0.73

areth

-0.71

 bloggers

-0.71

ï¸ı

-0.69

ror

-0.68

 GoPro

-0.67

abis

-0.67

 voic

-0.67

POSITIVE LOGITS

1.95

1.92

1.91

1.89

1.87

Activations Density 0.247%

years or dates mentioned as part of historical events

occurrences of the word "in" and its associated temporal context

No Comments

No Known Activations