INDEX

Explanations

words related to decrease or reduced actions or states

oai_token-act-pair · gpt-3.5-turbo

terms related to reduction or decline in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ansas

-0.72

wered

-0.68

giving

-0.64

oa

-0.63

ocratic

-0.62

Bio

-0.61

 Aval

-0.61

Issue

-0.61

types

-0.60

Reviewed

-0.60

POSITIVE LOGITS

 decrease

0.85

cember

0.84

 reduction

0.75

 decreases

0.75

 decreasing

0.71

 decreased

0.71

uce

0.70

(-

0.70

 Decre

0.69

 inhibited

0.68

Activations Density 0.021%

words related to decrease or reduced actions or states

terms related to reduction or decline in various contexts

No Comments

No Known Activations