INDEX

Explanations

mentions of actions or processes that involve lowering something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "lower" or its variations in relation to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Asia

-0.87

POL

-0.80

SPONSORED

-0.76

Phill

-0.71

Beast

-0.70

 Filip

-0.70

Pros

-0.70

 Raymond

-0.70

Pac

-0.69

present

-0.69

POSITIVE LOGITS

 lowering

1.26

 lowered

1.06

 inhib

0.97

baugh

0.96

 lowers

0.92

imar

0.90

 benches

0.88

undai

0.87

 slope

0.83

 carbohyd

0.83

Activations Density 0.009%

mentions of actions or processes that involve lowering something

instances of the word "lower" or its variations in relation to various contexts

No Comments

No Known Activations