INDEX

Explanations

words related to specific people or places, particularly those with the prefix 'Str'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "Str" followed by other characters

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

hyde

-0.80

ħĭ

-0.69

etheless

-0.68

¥µ

-0.68

eals

-0.67

tical

-0.67

peat

-0.66

vertising

-0.66

 Granted

-0.65

eph

-0.65

POSITIVE LOGITS

ategy

1.00

angling

0.94

atile

0.90

ands

0.89

ainer

0.89

ategic

0.89

angled

0.89

icken

0.87

agg

0.87

abo

0.86

Activations Density 0.011%

words related to specific people or places, particularly those with the prefix 'Str'

occurrences of the substring "Str" followed by other characters

No Comments

No Known Activations