INDEX

Explanations

phrases related to unexpected negative consequences or outcomes

oai_token-act-pair · gpt-3.5-turbo

terms related to failures or adverse outcomes, particularly involving "fire" as a metaphor

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

member

-0.70

agar

-0.69

said

-0.68

hi

-0.68

anson

-0.65

uala

-0.64

sal

-0.63

nih

-0.63

uv

-0.63

wra

-0.62

POSITIVE LOGITS

 tactics

0.68

aneously

0.68

iveness

0.66

 Healer

0.66

 Moreno

0.65

å§«

0.65

ANCE

0.65

icult

0.63

ļéĨĴ

0.63

acies

0.62

Activations Density 0.097%

phrases related to unexpected negative consequences or outcomes

terms related to failures or adverse outcomes, particularly involving "fire" as a metaphor

No Comments

No Known Activations