INDEX

Explanations

specific names and terms related to a political or news context

oai_token-act-pair · gpt-3.5-turbo

occurrences of specific names and identifiers within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

hered

-0.87

ted

-0.77

self

-0.75

TPS

-0.74

sheet

-0.69

ting

-0.69

tf

-0.68

FW

-0.68

 Insect

-0.67

ext

-0.66

POSITIVE LOGITS

aji

1.19

pora

1.03

ptions

0.94

ajor

0.92

veyard

0.89

ision

0.86

oti

0.84

Ú

0.84

Angelo

0.84

agara

0.83

Activations Density 0.009%

specific names and terms related to a political or news context

occurrences of specific names and identifiers within the text

No Comments

No Known Activations