INDEX

Explanations

phrases related to events being planned or orchestrated

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "staged" in various contexts

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

ittal

-0.88

anse

-0.87

ogy

-0.84

fol

-0.83

itte

-0.80

thood

-0.76

oft

-0.74

hani

-0.73

eeper

-0.71

esan

-0.71

POSITIVE LOGITS

 havoc

0.84

 barric

0.78

 staged

0.76

 revolt

0.75

 annex

0.74

 mock

0.74

 orchestrated

0.74

 Destruction

0.73

 demolition

0.72

 stunts

0.72

Activations Density 0.079%

phrases related to events being planned or orchestrated

occurrences of the word "staged" in various contexts

No Comments

No Known Activations