INDEX

Explanations

named entities related to locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'V' at various points in the document

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

İĭ

-0.70

 thereto

-0.69

 choke

-0.69

 bottleneck

-0.68

zona

-0.68

 Cerberus

-0.66

DPR

-0.66

 totality

-0.66

EStream

-0.64

SPD

-0.63

POSITIVE LOGITS

oby

1.06

erm

0.98

arl

0.95

aron

0.95

ris

0.94

anc

0.94

arm

0.93

arc

0.93

arr

0.91

olly

0.90

Activations Density 0.203%

named entities related to locations

occurrences of the letter 'V' at various points in the document

No Comments

No Known Activations