INDEX

Explanations

phrases related to estimates, figures, and statistical data

oai_token-act-pair · gpt-3.5-turbo

phrases related to estimates and guarantees

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

 Klux

-0.77

Interstitial

-0.73

issance

-0.70

ILE

-0.70

 Koch

-0.67

aucuses

-0.66

swick

-0.66

imeo

-0.64

Untitled

-0.64

EEK

-0.63

POSITIVE LOGITS

 estimating

0.86

 assigning

0.84

 interpretation

0.77

 predicting

0.75

 interpretations

0.74

 determining

0.73

 caus

0.73

 fortun

0.73

 validity

0.73

 estimate

0.72

Activations Density 0.707%

phrases related to estimates, figures, and statistical data

phrases related to estimates and guarantees

No Comments

No Known Activations