INDEX

Explanations

years or dates

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" and its variations in time-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

kids

-0.77

 texted

-0.74

Netflix

-0.72

zbollah

-0.70

paces

-0.70

 bloggers

-0.70

blogs

-0.69

hover

-0.67

ross

-0.67

wcs

-0.67

POSITIVE LOGITS

1.77

1.76

1.74

1.73

1.72

Activations Density 0.244%

years or dates

occurrences of the word "in" and its variations in time-related contexts

No Comments

No Known Activations