INDEX

Explanations

phrases or words that convey positive attributes or actions

oai_token-act-pair · gpt-3.5-turbo

terminology related to positive outcomes or effects

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

appings

-0.81

ptin

-0.80

oths

-0.79

puter

-0.79

adr

-0.78

conservancy

-0.76

neys

-0.74

ngth

-0.73

RAW

-0.73

arers

-0.72

POSITIVE LOGITS

 reinforcement

1.05

 affirm

0.92

 affirmation

0.90

 feedback

0.84

 outcome

0.83

vib

0.83

 positive

0.80

 portrayal

0.79

 outlook

0.77

 appraisal

0.76

Activations Density 0.028%

phrases or words that convey positive attributes or actions

terminology related to positive outcomes or effects

No Comments

No Known Activations