INDEX

Explanations

phrases indicating a strong commitment or promise to undertake an action

oai_token-act-pair · gpt-3.5-turbo

the word "vowed" and related expressions of commitment or promise

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

ateral

-0.74

APH

-0.70

Occ

-0.70

äºĶ

-0.70

nesota

-0.69

æŃ¦

-0.69

agnetic

-0.68

apy

-0.68

agate

-0.68

adjusted

-0.67

POSITIVE LOGITS

lessly

0.84

vow

0.83

 vows

0.83

 Trident

0.77

 vowed

0.76

lessness

0.73

fulness

0.72

 defiant

0.71

 anew

0.70

ctive

0.70

Activations Density 0.013%

phrases indicating a strong commitment or promise to undertake an action

the word "vowed" and related expressions of commitment or promise

No Comments

No Known Activations