INDEX

Explanations

statements or pieces of information that have been explicitly declared or affirmed

oai_token-act-pair · gpt-3.5-turbo

instances of the word "stated"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

brance

-0.71

vernment

-0.68

 sacked

-0.67

xtap

-0.67

agra

-0.66

 Carbuncle

-0.63

abies

-0.63

sites

-0.63

gone

-0.63

illard

-0.62

POSITIVE LOGITS

gow

0.92

 stated

0.83

 bluntly

0.75

 stating

0.73

 defaults

0.72

:"

0.71

orical

0.71

 states

0.70

:]

0.70

 mentions

0.69

Activations Density 0.028%

statements or pieces of information that have been explicitly declared or affirmed

instances of the word "stated"

No Comments

No Known Activations