INDEX

Explanations

names of individuals, specifically with a preference for the surname "Edwards"

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of the name "Edwards" in relation to legal or professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

efully

-0.90

ths

-0.82

fully

-0.80

asta

-0.79

ographed

-0.78

eful

-0.77

ghai

-0.74

ctica

-0.74

apest

-0.73

istically

-0.73

POSITIVE LOGITS

burgh

0.81

ignt

0.71

pires

0.70

pring

0.69

AFB

0.66

ville

0.65

mond

0.65

NR

0.64

Jr

0.64

Activations Density 0.036%

names of individuals, specifically with a preference for the surname "Edwards"

the repeated mention of the name "Edwards" in relation to legal or professional contexts

No Comments

No Known Activations