INDEX

Explanations

phrases related to influence or power

oai_token-act-pair · gpt-3.5-turbo

mentions of influence across various contexts and entities

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

TAG

-0.84

ITIES

-0.76

ft

-0.75

leigh

-0.72

yll

-0.70

Quotes

-0.68

atri

-0.68

Simple

-0.68

TH

-0.67

 Dill

-0.66

POSITIVE LOGITS

 pedd

1.16

 influence

0.99

 cooker

0.98

 influencing

0.96

 sway

0.92

 exerted

0.88

 influences

0.82

 shaping

0.82

 influenced

0.78

 multiplier

0.74

Activations Density 0.034%

phrases related to influence or power

mentions of influence across various contexts and entities

No Comments

No Known Activations