INDEX

Explanations

words related to quantitative measurement or assessment

oai_token-act-pair · gpt-3.5-turbo

terms related to indicators or measurements of various conditions or qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

©¶æ

-0.85

ahime

-0.82

ategory

-0.80

frey

-0.78

artney

-0.77

ernel

-0.76

LOAD

-0.74

lishing

-0.74

ŃĶ

-0.70

uthor

-0.70

POSITIVE LOGITS

 indicators

1.05

 markers

0.96

 indicator

0.86

 marker

0.86

 gauge

0.85

 correlate

0.78

gau

0.73

posts

0.73

 variables

0.72

mentioned

0.69

Activations Density 0.051%

words related to quantitative measurement or assessment

terms related to indicators or measurements of various conditions or qualities

No Comments

No Known Activations