INDEX

Explanations

action words related to technology and settings

oai_token-act-pair · gpt-3.5-turbo

verbs indicating actions related to activation or implementation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Press

-0.64

quart

-0.61

rehens

-0.61

hon

-0.59

bay

-0.59

bia

-0.59

nexus

-0.57

 Scand

-0.57

ibli

-0.56

Reb

-0.55

POSITIVE LOGITS

rul

0.74

 theirs

0.70

ado

0.67

KE

0.59

 yours

0.58

 refere

0.57

yles

0.56

 spree

0.56

 oneself

0.55

igation

0.55

Activations Density 0.714%

action words related to technology and settings

verbs indicating actions related to activation or implementation processes

No Comments

No Known Activations