INDEX

Explanations

instances of phrases related to trying or experimenting with something

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "try out."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cious

-0.69

antry

-0.68

aving

-0.67

VA

-0.66

 fabrication

-0.64

Ret

-0.61

eries

-0.61

``

-0.60

ellery

-0.58

ave

-0.58

POSITIVE LOGITS

fitted

0.75

stretched

0.71

doors

0.69

grown

0.69

smart

0.67

lived

0.66

flows

0.63

izabeth

0.62

Eck

0.62

ources

0.61

Activations Density 0.036%

instances of phrases related to trying or experimenting with something

instances of the phrase "try out."

No Comments

No Known Activations