INDEX

Explanations

phrases expressing opinions or thoughts

oai_token-act-pair · gpt-3.5-turbo

expressions of belief or anticipation regarding various topics

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

panic

-0.75

Shape

-0.73

Usage

-0.69

Individual

-0.67

Applic

-0.65

Attributes

-0.65

soever

-0.64

stroke

-0.62

thinkable

-0.62

pex

-0.62

POSITIVE LOGITS

 ourselves

1.16

 ours

0.77

our

0.75

 parted

0.72

 together

0.71

 tongues

0.66

 Braz

0.64

 mutually

0.62

yg

0.62

nesday

0.61

Activations Density 0.373%

phrases expressing opinions or thoughts

expressions of belief or anticipation regarding various topics

No Comments

No Known Activations