INDEX

Explanations

phrases or sentences indicating the presence of something within a particular entity

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "contain" and its variations

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

doms

-0.88

 Sabha

-0.82

lag

-0.66

straight

-0.66

 athlet

-0.66

 Airways

-0.62

laus

-0.62

hon

-0.60

urai

-0.60

Sport

-0.59

POSITIVE LOGITS

ãĤ£

0.80

 enough

0.78

 sufficient

0.77

 spoilers

0.77

nces

0.76

ãĥĸ

0.76

 lots

0.74

 traces

0.73

 provisions

0.73

ttes

0.73

Activations Density 0.052%

phrases or sentences indicating the presence of something within a particular entity

occurrences of the word "contain" and its variations

No Comments

No Known Activations