INDEX

Explanations

phrases related to contributing to or writing reports or articles

oai_token-act-pair · gpt-3.5-turbo

phrases indicating contributions or actions

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

Glass

-0.70

IED

-0.67

 clocks

-0.66

WIND

-0.64

CHAT

-0.64

Link

-0.63

TIME

-0.63

HUD

-0.61

hots

-0.60

naire

-0.60

POSITIVE LOGITS

 compensate

0.77

 create

0.73

 propagate

0.72

 strengthen

0.71

 shaping

0.71

 assist

0.70

 improve

0.70

 amplify

0.69

 elevate

0.69

 sustaining

0.68

Activations Density 0.048%

phrases related to contributing to or writing reports or articles

phrases indicating contributions or actions

No Comments

No Known Activations