INDEX

Explanations

mentions of political figures, organizations, and events

oai_token-act-pair · gpt-3.5-turbo

specific patterns or combinations of letters that may indicate proper nouns or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ãĥĩãĤ£

-0.79

ngth

-0.74

ãĥ¢

-0.71

ãĤ¼ãĤ¦ãĤ¹

-0.67

ãĤ®

-0.66

ãĤ¢ãĥ«

-0.65

ãĥī

-0.65

£ı

-0.65

ufact

-0.64

gage

-0.63

POSITIVE LOGITS

tip

0.75

orah

0.69

uit

0.67

arma

0.67

Tip

0.67

bush

0.66

spir

0.66

atron

0.66

RP

0.65

ayn

0.65

Activations Density 0.077%

mentions of political figures, organizations, and events

specific patterns or combinations of letters that may indicate proper nouns or identifiers

No Comments

No Known Activations