INDEX

Explanations

medical or legal terms related to injury or officiating

oai_token-act-pair · gpt-3.5-turbo

terms related to various roles and responsibilities, particularly in professional and service 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

yip

-0.79

ĨĴ

-0.71

theless

-0.70

cember

-0.70

emort

-0.67

vironment

-0.67

iard

-0.66

hower

-0.66

Monitor

-0.66

ITNESS

-0.65

POSITIVE LOGITS

rants

1.04

lov

0.95

ours

0.94

oured

0.93

outed

0.90

los

0.89

ilar

0.89

gins

0.86

ulatory

0.86

ration

0.85

Activations Density 0.074%

medical or legal terms related to injury or officiating

terms related to various roles and responsibilities, particularly in professional and service contexts

No Comments

No Known Activations