INDEX

Explanations

references to specific names or entities related to news, events, and locations

oai_token-act-pair · gpt-3.5-turbo

names of people or entities associated with specific events or discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

different

-0.69

²¾

-0.66

Ö¼

-0.65

otine

-0.64

»

-0.62

 destro

-0.61

ecause

-0.58

Magikarp

-0.57

aspers

-0.57

ggle

-0.53

POSITIVE LOGITS

.;

1.12

0.93

;;;;;;;;;;;;

0.91

.:

0.87

 Photograph

0.87

 âĵĺ

0.86

.,

0.86

};

0.84

 âĨĳ

0.84

<|endoftext|>

0.83

Activations Density 0.287%

references to specific names or entities related to news, events, and locations

names of people or entities associated with specific events or discussions

No Comments

No Known Activations