INDEX

Explanations

specific words related to the term "Fury" and geographic location mentions like "Fiji", as well as some specific names like "Gust" and "Vega"

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of specific titles or notable entities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

pocket

-0.83

kai

-0.77

organic

-0.77

izational

-0.76

repeat

-0.75

emark

-0.74

quo

-0.72

ership

-0.72

ä¸ī

-0.72

opathy

-0.71

POSITIVE LOGITS

 Fury

1.03

anche

0.83

rites

0.79

ous

0.73

ricanes

0.71

 Cutter

0.70

edIn

0.69

quit

0.69

burgh

0.69

 Alley

0.68

Activations Density 0.016%

specific words related to the term "Fury" and geographic location mentions like "Fiji", as well as some specific names like "Gust" and "Vega"

repeated mentions of specific titles or notable entities

No Known Activations