INDEX

Explanations

statements indicating uncertainty or lack of clarity

oai_token-act-pair · gpt-3.5-turbo

instances of uncertainty or ambiguity in statements

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

INT

-0.87

inse

-0.75

uilding

-0.74

atra

-0.72

ocard

-0.72

@#&

-0.71

emetery

-0.71

ructose

-0.70

onest

-0.70

onto

-0.70

POSITIVE LOGITS

 whether

0.78

comings

0.75

ether

0.68

icably

0.67

 Dragonbound

0.67

 conflicting

0.67

 unanimous

0.65

how

0.65

 indications

0.65

 chronological

0.64

Activations Density 0.017%

statements indicating uncertainty or lack of clarity

instances of uncertainty or ambiguity in statements

No Comments

No Known Activations