INDEX

Explanations

mentions of different locations within the text

oai_token-act-pair · gpt-3.5-turbo

the word "this" 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 @ 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

letes

-0.75

ickets

-0.74

ques

-0.72

lete

-0.72

cks

-0.71

onto

-0.70

 Izan

-0.68

onis

-0.67

rex

-0.66

stars

-0.65

POSITIVE LOGITS

 regard

1.25

 context

1.04

 vein

1.03

 particular

1.00

 vicinity

0.98

 manner

0.96

 circumstance

0.89

 week

0.89

 predicament

0.87

 scenario

0.86

Activations Density 0.056%

mentions of different locations within the text

the word "this" in various contexts

No Comments

No Known Activations