INDEX

Explanations

phrases related to boundaries or limits

oai_token-act-pair · gpt-3.5-turbo

the word "within" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

enez

-0.71

ãĥ£

-0.70

ãĥĵ

-0.70

ple

-0.69

ãĤ·ãĥ£

-0.68

ãĥĹ

-0.66

é¾į

-0.66

rod

-0.66

mil

-0.65

tec

-0.65

POSITIVE LOGITS

imore

0.89

isine

0.83

¥ŀ

0.77

ciating

0.75

izabeth

0.75

animate

0.74

ieth

0.70

atform

0.70

 parentheses

0.70

isode

0.69

Activations Density 0.026%

phrases related to boundaries or limits

the word "within" in various contexts

No Comments

No Known Activations