INDEX

Explanations

verbs and adjectives related to giving positive feedback

oai_token-act-pair · gpt-3.5-turbo

expressions of admiration or praise

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ramid

-0.78

bang

-0.71

soDeliveryDate

-0.71

itamin

-0.70

itol

-0.69

agnetic

-0.69

 proport

-0.67

claimer

-0.66

abouts

-0.66

ueller

-0.66

POSITIVE LOGITS

ifully

0.85

fully

0.80

him

0.77

 virtues

0.76

ably

0.74

 them

0.72

enance

0.70

ously

0.68

 bravery

0.68

Neh

0.67

Activations Density 0.115%

verbs and adjectives related to giving positive feedback

expressions of admiration or praise

No Comments

No Known Activations