INDEX

Explanations

phrases related to educational institutions, courses, and programs

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.97

glLoadIdentity

-0.70

ánchez

-0.68

glTexCoord

-0.66

SequentialGroup

-0.66

Enllaços

-0.62

posób

-0.62

noStroke

-0.60

 GenerationType

-0.60

glBind

-0.60

POSITIVE LOGITS

hcm

1.14

 saar

1.12

 indestru

1.05

 Suom

1.04

fordable

1.02

Elementary

1.01

 Elementary

1.00

 resear

0.99

 lele

0.98

 dises

0.96

Activations Density 0.500%

phrases related to educational institutions, courses, and programs

No Comments

No Known Activations