INDEX

Explanations

The neuron is looking for phrases related to causing a significant impact or change

oai_token-act-pair · gpt-3.5-turbo

phrases indicating significant changes or impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 consulted

-0.78

gat

-0.70

 aloud

-0.70

 followed

-0.70

çīĪ

-0.69

 preceded

-0.68

 forbids

-0.68

tackle

-0.68

replace

-0.68

 namely

-0.67

POSITIVE LOGITS

 entire

1.25

 effectiveness

1.19

 entirety

1.18

 viability

1.12

 notion

1.12

 likelihood

1.11

 perception

1.08

 impression

1.06

 usefulness

1.05

 overall

1.04

Activations Density 0.222%

The neuron is looking for phrases related to causing a significant impact or change

phrases indicating significant changes or impacts

No Comments

No Known Activations