INDEX

Explanations

names or surnames ending in 's'

oai_token-act-pair · gpt-3.5-turbo

instances of a specific character or symbol frequently mentioned 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 scattering

-0.74

 nurturing

-0.73

 yield

-0.72

 shelf

-0.71

 envelope

-0.71

 clinch

-0.70

 filler

-0.69

 disadvant

-0.68

 trapping

-0.68

 abound

-0.67

POSITIVE LOGITS

said

1.41

ï¸ı

1.37

wrote

1.13

sent

1.12

told

1.12

has

1.10

didn

1.02

should

1.01

answered

1.01

signed

1.00

Activations Density 0.139%

names or surnames ending in 's'

instances of a specific character or symbol frequently mentioned in various contexts

No Comments

No Known Activations

names or surnames ending in 's'

instances of a specific character or symbol frequently mentioned in various contexts

No Comments

No Known Activations