INDEX

Explanations

words related to salamanders and salaciousness

oai_token-act-pair · gpt-3.5-turbo

instances of the word "sal" and its variations throughout the text

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

 Dominion

-0.81

lihood

-0.81

STEP

-0.77

 Breed

-0.71

 Breaker

-0.69

gaard

-0.68

 derog

-0.68

urden

-0.67

 Reboot

-0.67

 Sets

-0.66

POSITIVE LOGITS

utations

1.16

mone

1.05

istry

1.00

udos

0.98

aunch

0.97

utation

0.96

osal

0.92

ience

0.90

isbury

0.90

acious

0.90

Activations Density 0.010%

words related to salamanders and salaciousness

instances of the word "sal" and its variations throughout the text

No Comments

No Known Activations