INDEX

Explanations

phrases or terms related to composition or makeup

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of being "made up" or constructed from various components

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

IFrame

Link

Negative Logits

 Clicker

-0.70

BIL

-0.70

FK

-0.67

natureconservancy

-0.63

Trade

-0.59

 Decay

-0.57

 depletion

-0.55

Export

-0.54

ERO

-0.54

redo

-0.53

POSITIVE LOGITS

by

1.09

BY

0.88

 aback

0.86

by

0.84

monton

0.76

sole

0.72

alian

0.70

bys

0.70

river

0.67

swing

0.67

Activations Density 0.089%

phrases or terms related to composition or makeup

phrases related to the concept of being "made up" or constructed from various components

No Known Activations