INDEX

Explanations

comparisons or contrasts using the word "like"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "like" 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

VERTISEMENT

-0.81

arbon

-0.77

ccording

-0.70

ids

-0.70

 proport

-0.69

esson

-0.69

opian

-0.69

ahime

-0.68

 undermin

-0.68

igious

-0.68

POSITIVE LOGITS

lihood

1.26

 yours

1.08

 ours

1.03

 myself

0.98

 Pamela

0.94

 hers

0.92

lier

0.92

 Erik

0.91

liest

0.86

 Robert

0.85

Activations Density 0.082%

comparisons or contrasts using the word "like"

instances of the word "like" in various contexts

No Comments

No Known Activations