INDEX

Explanations

the pattern "Der" with varying numerical values associated with it

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Der" 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Dragonbound

-0.78

hetti

-0.73

 Samoa

-0.69

sburgh

-0.65

eous

-0.62

[|

-0.62

hews

-0.61

 Elephant

-0.60

packing

-0.60

ships

-0.59

POSITIVE LOGITS

mal

1.03

bys

0.99

bil

0.94

iving

0.93

ricks

0.92

 Spiegel

0.91

isively

0.91

ived

0.89

ivation

0.86

rick

0.82

Activations Density 0.021%

the pattern "Der" with varying numerical values associated with it

occurrences of the word "Der" in various contexts

No Comments

No Known Activations