INDEX

Explanations

phrases related to providing information or explanations, possibly in a formal or technical context

oai_token-act-pair · gpt-3.5-turbo

phrases related to significant events or actions involving individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 aven

-0.72

 agriculture

-0.71

 gren

-0.71

 masked

-0.70

 forestry

-0.70

net

-0.69

 societies

-0.69

 resent

-0.69

istration

-0.69

 infl

-0.69

POSITIVE LOGITS

Own

1.20

 Affect

1.14

 Relationship

1.14

 Approach

1.06

 Appro

1.05

 Course

1.05

 Guys

1.04

 Clause

1.02

 Character

1.02

 Stupid

1.02

Activations Density 0.541%

phrases related to providing information or explanations, possibly in a formal or technical context

phrases related to significant events or actions involving individuals or groups

No Comments

No Known Activations