INDEX

Explanations

words related to specific professions or occupations

oai_token-act-pair · gpt-3.5-turbo

words that denote roles or professions ending in specific suffixes

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

ASED

-0.71

 increments

-0.68

 Territories

-0.67

 Warden

-0.67

 conviction

-0.61

 bilateral

-0.60

 implication

-0.60

 Farm

-0.58

 Investments

-0.57

 Thing

-0.57

POSITIVE LOGITS

hip

1.42

hips

1.22

paces

1.16

ervatives

1.06

mith

1.03

heet

0.98

peak

0.97

pace

0.96

0.93

hare

0.92

Activations Density 0.134%

words related to specific professions or occupations

words that denote roles or professions ending in specific suffixes

No Comments

No Known Activations