INDEX

Explanations

references to being influenced or influenced by something

oai_token-act-pair · gpt-3.5-turbo

references to influences and their impact in various contexts

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

ft

-0.78

ITIES

-0.77

çĦ

-0.72

VK

-0.70

zar

-0.69

dain

-0.68

heart

-0.68

TY

-0.68

clamation

-0.68

ITY

-0.67

POSITIVE LOGITS

 influencing

1.01

 shaping

0.97

 influences

0.96

 pedd

0.90

 influence

0.90

kson

0.83

 cooker

0.82

 influenced

0.80

 influ

0.77

cules

0.75

Activations Density 0.047%

references to being influenced or influenced by something

references to influences and their impact in various contexts

No Comments

No Known Activations