INDEX

Explanations

references to or descriptions of a specific individual identified as "guy."

oai_token-act-pair · gpt-3.5-turbo

repeated references to the term "guy" and its variations 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Parables

-0.73

tnc

-0.72

 Supplement

-0.71

illus

-0.68

iff

-0.68

EMBER

-0.67

Import

-0.67

èª

-0.66

theless

-0.66

rawdownloadcloneembedreportprint

-0.66

POSITIVE LOGITS

holes

0.85

who

0.78

abase

0.76

 fucked

0.74

hattan

0.73

hole

0.73

 damned

0.72

 pissed

0.70

bru

0.70

 else

0.70

Activations Density 0.038%

references to or descriptions of a specific individual identified as "guy."

repeated references to the term "guy" and its variations in various contexts

No Comments

No Known Activations