INDEX

Explanations

action verbs related to human behavior

oai_token-act-pair · gpt-3.5-turbo

action verbs indicating influence or interaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

iscons

-0.70

issance

-0.65

 destro

-0.64

 encount

-0.61

 agre

-0.59

 COURT

-0.59

Instance

-0.59

 enthusi

-0.58

 afore

-0.58

 APPLIC

-0.57

POSITIVE LOGITS

ings

1.01

ingly

0.92

eth

0.83

adelphia

0.81

 themselves

0.76

fully

0.74

INGS

0.71

geries

0.70

ments

0.70

able

0.70

Activations Density 0.522%

action verbs related to human behavior

action verbs indicating influence or interaction

No Comments

No Known Activations