INDEX

Explanations

instances of the word "shark"

oai_token-act-pair · gpt-3.5-turbo

references to sharks

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ISTER

-0.82

ories

-0.76

 Hemp

-0.72

ISION

-0.67

haar

-0.66

ijah

-0.64

ndra

-0.64

onsense

-0.64

mble

-0.63

icably

-0.63

POSITIVE LOGITS

ulic

0.96

 fins

0.88

fish

0.84

vati

0.82

izont

0.80

 sharks

0.80

mong

0.80

iform

0.78

bite

0.77

 Sharks

0.77

Activations Density 0.018%

instances of the word "shark"

references to sharks

No Comments

No Known Activations