INDEX

Explanations

phrases related to official stances or positions on various subjects

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "on," particularly in political or positional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ennes

-0.80

ults

-0.72

::::::::

-0.68

ENTS

-0.67

ï¸ı

-0.67

SourceFile

-0.67

MODE

-0.67

ARM

-0.65

BILITIES

-0.65

ACT

-0.65

POSITIVE LOGITS

 behalf

1.65

erous

1.02

yx

0.96

etheless

0.94

 steroids

0.92

etime

0.89

 Capitol

0.87

 matters

0.86

shore

0.85

site

0.85

Activations Density 0.233%

phrases related to official stances or positions on various subjects

occurrences of the word "on," particularly in political or positional contexts

No Comments

No Known Activations