INDEX

Explanations

sport-related terms and positions like "OT", "DL", "DB", "LB", and "RB"

oai_token-act-pair · gpt-3.5-turbo

references to specific positions or roles in a sports context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ãĥ¼ãĥĨ

-0.83

Elect

-0.78

ãĥĬ

-0.76

flies

-0.75

;;;;;;;;;;;;

-0.72

ibel

-0.72

illa

-0.69

 Bosnia

-0.68

ãĤ±

-0.68

 Camel

-0.67

POSITIVE LOGITS

OT

1.10

ibrary

0.82

DL

0.80

TO

0.78

endum

0.77

 linemen

0.76

OL

0.75

KO

0.74

DL

0.73

Ps

0.73

Activations Density 0.009%

sport-related terms and positions like "OT", "DL", "DB", "LB", and "RB"

references to specific positions or roles in a sports context

No Comments

No Known Activations