INDEX

Explanations

names or references related to "Ha"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Ha" followed by various contextual mentions

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

manship

-0.87

eenth

-0.85

âķĲ

-0.82

eers

-0.82

icipated

-0.78

*/(

-0.77

hips

-0.77

ĳå£«

-0.76

ments

-0.74

ãĥ¼ãĥĨ

-0.71

POSITIVE LOGITS

irst

1.05

vel

1.03

pless

0.96

ifa

0.96

Ha

0.93

iku

0.93

iley

0.92

aretz

0.86

oney

0.85

iky

0.85

Activations Density 0.011%

names or references related to "Ha"

occurrences of the term "Ha" followed by various contextual mentions

No Comments

No Known Activations