INDEX

Explanations

words related to conflicts and tensions, particularly in political contexts

oai_token-act-pair · gpt-3.5-turbo

commas and conjunctions indicating complex sentence structures or lists of events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orem

-0.84

iris

-0.78

pheus

-0.72

thood

-0.72

ynt

-0.69

 Anyway

-0.69

 Memor

-0.68

sein

-0.67

+++

-0.67

llular

-0.67

POSITIVE LOGITS

 prompting

1.44

 sparking

1.17

 forcing

1.15

 culminating

1.08

 triggering

1.04

 causing

1.04

 fueling

1.02

 provoking

0.98

fue

0.93

 disrupting

0.93

Activations Density 0.252%

words related to conflicts and tensions, particularly in political contexts

commas and conjunctions indicating complex sentence structures or lists of events

No Comments

No Known Activations