INDEX

Explanations

commands or instructions in a technical context

oai_token-act-pair · gpt-3.5-turbo

colons followed by instructions or statements in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 insurer

-0.78

 eaves

-0.75

 trouble

-0.73

 troubles

-0.71

undai

-0.68

illance

-0.67

 oversight

-0.65

yan

-0.65

 tremend

-0.65

 reservation

-0.64

POSITIVE LOGITS

 Provided

1.01

 https

0.98

 http

0.97

 Logged

0.90

YES

0.89

https

0.86

http

0.85

 namely

0.80

$$$$

0.80

0.79

Activations Density 0.152%

commands or instructions in a technical context

colons followed by instructions or statements in technical contexts

No Comments

No Known Activations