INDEX

Explanations

phrases related to receiving or being granted something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "given" and its various 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 vein

-0.66

uras

-0.60

idine

-0.59

Zone

-0.57

 sect

-0.57

``(

-0.57

 ethic

-0.57

stem

-0.57

_.

-0.56

ouse

-0.55

POSITIVE LOGITS

ĸļ

0.83

enced

0.77

ãĥĥãĥĪ

0.74

 permission

0.74

ãĥ¯

0.72

ãĥ¼ãĥĨ

0.69

ãĥį

0.68

 watered

0.68

rious

0.66

by

0.65

Activations Density 0.081%

phrases related to receiving or being granted something

instances of the word "given" and its various contexts

No Comments

No Known Activations