INDEX

Explanations

words related to intrusive medical procedures and related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to intelligence and its various forms or measures

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

 Seym

-0.66

 Panda

-0.62

 flats

-0.62

steen

-0.59

 generously

-0.59

upl

-0.59

iage

-0.58

 broom

-0.57

 minimized

-0.57

ãĢĲ

-0.57

POSITIVE LOGITS

LECT

0.77

acy

0.74

ersion

0.72

ATER

0.72

ater

0.70

lycer

0.70

cedented

0.70

igent

0.68

thora

0.68

igraph

0.68

Activations Density 0.068%

words related to intrusive medical procedures and related terms

terms related to intelligence and its various forms or measures

No Comments

No Known Activations