INDEX

Explanations

dates and locations expressed as cardinal numbers

oai_token-act-pair · gpt-3.5-turbo

negative connotations or mentions of conflict

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

advertisement

-1.10

ÂŃ

-1.03

Advertisements

-0.84

risome

-0.77

âĢ³

-0.74

 âĢ¦"

-0.74

âĢ¦."

-0.71

âĢ²

-0.69

âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦

-0.69

ADVERTISEMENT

-0.69

POSITIVE LOGITS

2.98

--

1.61

 ï¿½

1.56

---

1.41

--

1.35

–

1.25

"-

1.25

(-

1.22

1.21

-->

1.19

Activations Density 0.061%

dates and locations expressed as cardinal numbers

negative connotations or mentions of conflict

No Comments

No Known Activations