INDEX

Explanations

information regarding examining or investigation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "examine" 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 @ 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

âĹ¼

-0.77

Torrent

-0.71

gren

-0.69

activated

-0.67

fires

-0.67

cil

-0.66

cell

-0.66

loaded

-0.65

fall

-0.62

lua

-0.62

POSITIVE LOGITS

ively

0.95

ĸļ

0.84

osterone

0.80

mble

0.79

abilia

0.77

alus

0.76

ury

0.76

 Probe

0.74

 favorably

0.73

issance

0.73

Activations Density 0.032%

information regarding examining or investigation

instances of the word "examine" and its variations

No Comments

No Known Activations