INDEX

Explanations

mentions of the year "2020."

oai_token-act-pair · gpt-3.5-turbo

references to the year 2020 and future projections

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

Reviewer

-0.91

irez

-0.68

pat

-0.61

itcher

-0.60

[*

-0.58

à©

-0.58

 mortar

-0.57

agh

-0.57

 copies

-0.56

 opinion

-0.56

POSITIVE LOGITS

3.87

2.82

2.77

2.74

2.71

2.64

2.61

2.58

2.35

1.97

Activations Density 0.008%

mentions of the year "2020."

references to the year 2020 and future projections

No Comments

No Known Activations