INDEX

Explanations

mentions of predatory behavior or interactions involving prey

oai_token-act-pair · gpt-3.5-turbo

terms related to prey in ecological contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

aan

-0.69

olkien

-0.69

 Kubrick

-0.66

 Athletics

-0.64

 PRESIDENT

-0.62

helle

-0.62

 Zurich

-0.62

 McKenna

-0.62

 Prague

-0.60

 Pace

-0.59

POSITIVE LOGITS

fish

0.83

 prey

0.82

ele

0.76

 vanquished

0.74

brates

0.74

itives

0.74

wl

0.72

 Incarn

0.71

 eaten

0.71

pillar

0.71

Activations Density 0.034%

mentions of predatory behavior or interactions involving prey

terms related to prey in ecological contexts

No Comments

No Known Activations