INDEX

Explanations

names or terms related to organizations or events

oai_token-act-pair · gpt-3.5-turbo

references to specific names or abbreviations, likely related to organizations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

*/(

-0.80

worthiness

-0.76

theless

-0.70

bread

-0.66

tons

-0.66

stage

-0.64

sburg

-0.64

lain

-0.64

ski

-0.62

swer

-0.61

POSITIVE LOGITS

Ã±

1.16

ordan

1.09

agra

1.09

Ã±a

1.08

abetes

1.08

pper

1.07

ablo

1.06

enna

1.04

orno

1.02

qq

1.02

Activations Density 0.075%

names or terms related to organizations or events

references to specific names or abbreviations, likely related to organizations or entities

No Comments

No Known Activations