INDEX

Explanations

phrases related to positivity and favorable outcomes

oai_token-act-pair · gpt-3.5-turbo

references to positive outcomes or sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

oths

-0.85

ngth

-0.82

atum

-0.81

puter

-0.81

ptin

-0.79

appings

-0.76

adr

-0.73

alian

-0.72

hid

-0.72

neys

-0.72

POSITIVE LOGITS

 reinforcement

1.02

 outlook

0.96

 outcome

0.95

vib

0.94

 feedback

0.94

 affirm

0.89

 affirmation

0.86

 appraisal

0.85

 outcomes

0.84

 attitude

0.84

Activations Density 0.041%

phrases related to positivity and favorable outcomes

references to positive outcomes or sentiments

No Comments

No Known Activations