INDEX

Explanations

words related to geographical locations, particularly countries

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of locations and geographical entities

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

cube

-0.71

kid

-0.71

bread

-0.69

worn

-0.65

Ö¼

-0.64

iT

-0.63

better

-0.62

starter

-0.62

sheet

-0.61

å¤©

-0.61

POSITIVE LOGITS

Ã°

1.09

Ã±

0.91

veland

0.89

velength

0.84

cci

0.84

veyard

0.82

ignt

0.82

ÄŁ

0.79

zza

0.79

zzi

0.79

Activations Density 0.012%

words related to geographical locations, particularly countries

proper nouns, particularly names of locations and geographical entities

No Comments

No Known Activations